diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..202871cc377ba767536dd574e71be857fc40b502 --- /dev/null +++ b/config.json @@ -0,0 +1,34 @@ +{ + "_name_or_path": "./gianthydra", + "architectures": [ + "MixtralForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 4096, + "model_type": "mixtral", + "num_attention_heads": 64, + "num_experts_per_tok": 2, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "num_local_experts": 4, + "output_router_logits": false, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "router_aux_loss_coef": 0.001, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.37.2", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c20e2cf5ab6e5f02fa5086c642cc0c346e3c4ced --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.37.2", + "use_cache": false +} diff --git a/model-00001-of-00201.safetensors b/model-00001-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59075d6501a81ab55216739117d23c80f2be662d --- /dev/null +++ b/model-00001-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:510176a48d72902ac5ecb133257286150049b0dd61f56c4ab1b0dc792c2eddb9 +size 4471260248 diff --git a/model-00002-of-00201.safetensors b/model-00002-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e07c7900f6d45b0a5226206ff8a37cb6a89fa3e8 --- /dev/null +++ b/model-00002-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1d723e8af07415a60a5ed59fe26841558d463c7fa18bb1397d66715e3afec6 +size 4697621160 diff --git a/model-00003-of-00201.safetensors b/model-00003-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ba77d897f26fd23dcfd4b321c9d561d882a6f9f --- /dev/null +++ b/model-00003-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70b9ff8d8387de3432a3f691924e78a4f71812c6acb6e52f39820b30e08c8a23 +size 4362274128 diff --git a/model-00004-of-00201.safetensors b/model-00004-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f31f2db8a3d5f41f49995cd46e47139c8287477 --- /dev/null +++ b/model-00004-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90d54ac75e956eac7cbc7d2c5c1d491b4ca0fc7de3bd73b4bff4e313667ee35b +size 4697621160 diff --git a/model-00005-of-00201.safetensors b/model-00005-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a7069c29ccee77ec1a39cc30a61b718676e0a2d3 --- /dev/null +++ b/model-00005-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdac281289add341da239eee538d139d334af921d29a12885462be7391b7a6e3 +size 4697621160 diff --git a/model-00006-of-00201.safetensors b/model-00006-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b366f82a2e6556912dd5e7e63af40038b8734d6f --- /dev/null +++ b/model-00006-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ee21f0110b662a3e699bcc01f61f103e38d22d08e7f2f0aa468b80540aa3013 +size 4362274128 diff --git a/model-00007-of-00201.safetensors b/model-00007-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4343b29058354c88dc64c035370d9634f35dd197 --- /dev/null +++ b/model-00007-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6daf30af231e1d2184c53726f6f99aafa7da6811e5ec2d8e1b279d4aa950910 +size 4697621160 diff --git a/model-00008-of-00201.safetensors b/model-00008-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a410524ef2e8656b28b308218a7ecb3693452be1 --- /dev/null +++ b/model-00008-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff61de5aba6feee62fa32c33125f3ea147ad6d2f486093ec2f27266c20b500f +size 4999677048 diff --git a/model-00009-of-00201.safetensors b/model-00009-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..354c1ff8b8f8e11d060b0c203ed6bcda5358973f --- /dev/null +++ b/model-00009-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6344d7c963091c486b7ed07e100b838484b5bce79dcd73efc5e79de3a8ec1cb2 +size 4999742472 diff --git a/model-00010-of-00201.safetensors b/model-00010-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e3189cda16b9cc93065fdb257d7359cc80d733f --- /dev/null +++ b/model-00010-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:174da2e4365d1ed5e09e4e0129f599ac6f6ce7d0772e638ca9fefb0b3628e8e9 +size 4697621160 diff --git a/model-00011-of-00201.safetensors b/model-00011-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3cdda1ac2236d5be68cdc19903aff29670b5a75b --- /dev/null +++ b/model-00011-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c7e41230bbc6f75a2da7e7a26ffcc4d411132a1955b30511f9a44a3b1f70c4e +size 4362274128 diff --git a/model-00012-of-00201.safetensors b/model-00012-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5281665ece85015a9767f19a4be4ded224b4ddde --- /dev/null +++ b/model-00012-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52813b32615f5e77bc170fe69e0a5c96feb2ea994ad0f4d69a7a27e5877b4255 +size 4697621160 diff --git a/model-00013-of-00201.safetensors b/model-00013-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f642bd139cc48668cac0475b35aa71f64487d358 --- /dev/null +++ b/model-00013-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3411dfbe187eb9f27d9ede2faa51d9bf6501cae55b5c45fcdd53018c94400d2 +size 4999677048 diff --git a/model-00014-of-00201.safetensors b/model-00014-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..939cd947133f5df65b4f8d8fc4a817bb76f5b7a8 --- /dev/null +++ b/model-00014-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3607b0a308a6d0a6e7f1cc82c88195ba9650760d547fed64a294084bbe8c0903 +size 4999742472 diff --git a/model-00015-of-00201.safetensors b/model-00015-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e8754dccc24efab5c69109f3888dfa01bd9fa3b0 --- /dev/null +++ b/model-00015-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8b4cbc134e17e8d4761b2b93ee827f0dbaac072c4006b5e133835a1af3820b8 +size 4697621160 diff --git a/model-00016-of-00201.safetensors b/model-00016-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff462b201467f7993a7510be3c7ad59f0ca54179 --- /dev/null +++ b/model-00016-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:387438f39f6d93f67d76806e0e1ee08fadf34cced4c58d8517827de99f8ac910 +size 4362274128 diff --git a/model-00017-of-00201.safetensors b/model-00017-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..871bcb58ea15d72b02ca18cc366738ef305966a4 --- /dev/null +++ b/model-00017-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc7d1efccfb33e7dee4312bd4b267c1c58ca4202c24402048b5f7597b4823f7 +size 4697621160 diff --git a/model-00018-of-00201.safetensors b/model-00018-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..365f66fe2bc2ecb26afb584a0c2c53a0bed6c3db --- /dev/null +++ b/model-00018-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faabc9f5889c35689f15380c5570051b1ff97ad555a9aa5e4b1acfdba378b3ee +size 4999677048 diff --git a/model-00019-of-00201.safetensors b/model-00019-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..779a96f6a701b9740fe5d5838e9147e707b8d7a8 --- /dev/null +++ b/model-00019-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c491dd97738beb840e2be54b18b4e4ac361e75bfa4ee2a93e36931db73b9d76 +size 4999742472 diff --git a/model-00020-of-00201.safetensors b/model-00020-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d1926b62d83a502642315d9876d6e7be25f8deda --- /dev/null +++ b/model-00020-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3cf13479f07de09e166369906dedc73e8a4c4aa1b8dd8bf9c912bda7f97dad7 +size 4697621160 diff --git a/model-00021-of-00201.safetensors b/model-00021-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c2b2e004f5b7bf5510cef70bd9c4dce3543ccf3 --- /dev/null +++ b/model-00021-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb3b2b9164e1fe8dfd1798b85284192041ee7bc4819e39472e7c1441c32d2c7b +size 4362274128 diff --git a/model-00022-of-00201.safetensors b/model-00022-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4fafc5e7f2add8d9a334607fa2aeac16b79f8838 --- /dev/null +++ b/model-00022-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0e26dd8f9e9e4d09ad0bd3111910d4c3a10efeb1d10ea9a39f82099c61b134 +size 4697621160 diff --git a/model-00023-of-00201.safetensors b/model-00023-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8bdba8944ac62cf357343d6e88bb69b94967baf8 --- /dev/null +++ b/model-00023-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf6a944439c121af7a10f9f7f38ab48e314b90743ff2ab1d47dd865d06a60fe +size 4999677048 diff --git a/model-00024-of-00201.safetensors b/model-00024-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..660f7b77d2dd0976eaa4eb440ba84184c5a967cf --- /dev/null +++ b/model-00024-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622a7b55ea6b40dc825a3261834080bb0b48b5f748594528adca93c4bd258027 +size 4999742472 diff --git a/model-00025-of-00201.safetensors b/model-00025-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc1d17b14b7c9373b4bb4a6d68ee2a967a55a11e --- /dev/null +++ b/model-00025-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:280f460e27719b2d4bbc86f23ced27c4b7e1ecc01a9ec902c8c1a6d8483572b8 +size 4697621160 diff --git a/model-00026-of-00201.safetensors b/model-00026-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7233bbb826ae682e48318d2dcf2da2a5d8c38a5 --- /dev/null +++ b/model-00026-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b91b968ce35564a5a793d153cc41acc3ebe34cc1c2978bd16447018b1a8cb00 +size 4362274136 diff --git a/model-00027-of-00201.safetensors b/model-00027-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe9c55d939f67e9fe9a73af2d5985550dca3f6f5 --- /dev/null +++ b/model-00027-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:470c380514cc20e7cd763b9bc42e1b0858242c4fadba6581f9d4838903c6bd27 +size 4697621168 diff --git a/model-00028-of-00201.safetensors b/model-00028-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..076687717a550bb5eabd8e958ffa510561c71823 --- /dev/null +++ b/model-00028-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:482edf2b7e445f9829c0ab2d6f9ce30f4fc92ee524a66e8843cf1230db5f8b3c +size 4999677056 diff --git a/model-00029-of-00201.safetensors b/model-00029-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6754434d25768dab10832e413d97dc0dba2c12dc --- /dev/null +++ b/model-00029-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1ac89f7c7b7ceb8c9ae29771395607a501f845dfadfdeaefeb08521606f9520 +size 4999742480 diff --git a/model-00030-of-00201.safetensors b/model-00030-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dbd31ee66c9233397d5bf154c43a0bf616cb290b --- /dev/null +++ b/model-00030-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7335ac561a2732ca8e1a933256b591723adc81213eca6582e7585697b46736c6 +size 4697621168 diff --git a/model-00031-of-00201.safetensors b/model-00031-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a420141b6287d5585be85e25b4f81293802874d --- /dev/null +++ b/model-00031-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849cf8779c007f802b1c00491bc9443055a718d5fb079c72d8ce47d1633b4858 +size 4362274144 diff --git a/model-00032-of-00201.safetensors b/model-00032-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18cff910a640b627e7d755d766eb44a1d8b72f6c --- /dev/null +++ b/model-00032-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e67ded99b4290ae672e255160725659f9d895fbccac23584246bbfbbceadbd54 +size 4697621168 diff --git a/model-00033-of-00201.safetensors b/model-00033-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7a010d641726eb50732e56153aaad94c983bd6f --- /dev/null +++ b/model-00033-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a488f2af2430764200760f2cf7b015dc1f9b1c8f257182de28f24f8b476a6e02 +size 4999677056 diff --git a/model-00034-of-00201.safetensors b/model-00034-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e09d9fdae586ace2b705fbf2ba2ee5c6e67917c5 --- /dev/null +++ b/model-00034-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a261940d3cdfc7ec7874722eb8a92a3088bbdb217bd916af80e05351ec16fa4 +size 4999742480 diff --git a/model-00035-of-00201.safetensors b/model-00035-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0a0bb2816aef88f7fcb6765825be99385822a896 --- /dev/null +++ b/model-00035-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12681f117d6fda8f0147bee0ea4ca39a7e7195d8ab3f2c899e819f11e0192917 +size 4697621168 diff --git a/model-00036-of-00201.safetensors b/model-00036-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ef66f69239f47cbc4eb0fd896cafee6cdc9054c --- /dev/null +++ b/model-00036-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6d8bf5f153aa79addaedb6a5676f588e9b96f00413ed871dbbe77ee17fc3b7 +size 4362274144 diff --git a/model-00037-of-00201.safetensors b/model-00037-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..334e5dce8f3e6d348e1b000b4136a70c7aa9750f --- /dev/null +++ b/model-00037-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61305834df92f9db558276beccc0ffea8368f60fe5f5e866f7bd3fda726bc55c +size 4697621168 diff --git a/model-00038-of-00201.safetensors b/model-00038-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ff82f5a1ecf85e9bb90e19feb28caed81e77174 --- /dev/null +++ b/model-00038-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3a1975d6701a159ea79fb46dcb6879e227b3f0f9e470882544f37065a25268f +size 4999677056 diff --git a/model-00039-of-00201.safetensors b/model-00039-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f5d311da0ad0cccddddf08e23a6880f9dc1f0bf4 --- /dev/null +++ b/model-00039-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96ea3217d2d650785c19e9ee7c15bcc79b4d26306c06ee84e03e2da301579d8a +size 4999742480 diff --git a/model-00040-of-00201.safetensors b/model-00040-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5771c26a2d3fd030c897ba5e72568897225029d8 --- /dev/null +++ b/model-00040-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a581abee18103482961cd171f97118ee7de6a0808783d5cfb498118f44fb74 +size 4697621168 diff --git a/model-00041-of-00201.safetensors b/model-00041-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c23e715963fec87cbe48c94c46fec6617ccee952 --- /dev/null +++ b/model-00041-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8296e2f117ed7ed953c18c5c1605d50505a3e8e11c6545cf76e108f67b11ebea +size 4362274144 diff --git a/model-00042-of-00201.safetensors b/model-00042-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0932eb0f597aaac481602025976a8354649dcda4 --- /dev/null +++ b/model-00042-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:589a45e0722415cb79fe6cadc9b1d0ecc30f998c2ee0928dc7ba385b69e135d7 +size 4697621168 diff --git a/model-00043-of-00201.safetensors b/model-00043-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dd838a103cf409fae2ca149d71f1dc6ea9514b8b --- /dev/null +++ b/model-00043-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08e1765cfb4c65d6e898e3d567f0dfb985167117ab5dafd1f773b3250ed5f409 +size 4999677056 diff --git a/model-00044-of-00201.safetensors b/model-00044-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5fceabe0358ac705a3e59020ca6a6d668feb2ff --- /dev/null +++ b/model-00044-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c739a03f221cb5653856d1c4842b6fc225e28f52f5573d85fc032b5a1687a77f +size 4999742480 diff --git a/model-00045-of-00201.safetensors b/model-00045-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dba518e0e737fa5fc0fbdbb88c6611f6cb54d395 --- /dev/null +++ b/model-00045-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760ef5a75be203f04d5a823afb56095a92e906678acb2343316cffea94b1d6d6 +size 4697621168 diff --git a/model-00046-of-00201.safetensors b/model-00046-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c80628d70b81cc179e40f12fbf4b56cd906930b --- /dev/null +++ b/model-00046-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:776d0670887a11c19c3818d5edaadd51a95c516a97626f386ce11d4756cf84d1 +size 4362274144 diff --git a/model-00047-of-00201.safetensors b/model-00047-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c98fb5ba6d8b4e56eb0eb14436c3cf17b9a4838b --- /dev/null +++ b/model-00047-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:739a9e9f62b3d10f47344534d44659914d1ef052c8fd1c431bbd1aa603350b79 +size 4697621168 diff --git a/model-00048-of-00201.safetensors b/model-00048-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69e2ed0a0f2ab776a0176af55bf93144a0f0f212 --- /dev/null +++ b/model-00048-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d24b31e322d96479f3337daa952ed65ca487b7cd69043f00796c0bf1048db2 +size 4999677056 diff --git a/model-00049-of-00201.safetensors b/model-00049-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af4b959b72269b1e6da3bf310f3ac09832a82ecf --- /dev/null +++ b/model-00049-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dedd157f66822f9b44b4df364575c0b9d4d94bc8550c417fed7cd95363a487cf +size 4999742480 diff --git a/model-00050-of-00201.safetensors b/model-00050-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..74a12b6b026151829fe35f1553a04b1ad103a3b4 --- /dev/null +++ b/model-00050-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a807cd61717ec70469f5024711a2c5abfac0b33ee3c564b7e16b2969186ab1e6 +size 4697621168 diff --git a/model-00051-of-00201.safetensors b/model-00051-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0db2d5ae71c68cbfd9fc90c45d34b70887b46f4f --- /dev/null +++ b/model-00051-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0445b70772b8fc3413655cb969c857ab226cfb2509ce053c708e064475467431 +size 4362274144 diff --git a/model-00052-of-00201.safetensors b/model-00052-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a0411e1b9bb77419b787f8ea51b52d866841f9f --- /dev/null +++ b/model-00052-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3afdab7794be4f6a67ee3810d6ffb77437cf46772aa4095bfb916efb7addf4a +size 4697621168 diff --git a/model-00053-of-00201.safetensors b/model-00053-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5853c30262c5ce93279bdb02336b4cdb2c8c58dc --- /dev/null +++ b/model-00053-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc2324620b51ccc0cfe97806f9b6fc9a08883837e6a2d6d47ac41605145767ef +size 4999677056 diff --git a/model-00054-of-00201.safetensors b/model-00054-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..27609356279a70b9e3dc0c32f68ef7108e26fcff --- /dev/null +++ b/model-00054-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02c8278027419cc297dc67ee8fe1cd244931d26769ce66ef05e4f703d9adbf01 +size 4999742480 diff --git a/model-00055-of-00201.safetensors b/model-00055-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a7c9d2877cc576529c37810faaebfbfa7259467 --- /dev/null +++ b/model-00055-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29896b30952fea3c6b6389af0135bcf9b9f2c6e9e42f6397a876d6a6795ef6bc +size 4697621168 diff --git a/model-00056-of-00201.safetensors b/model-00056-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..752fb972fe38c6371af4f6d4cd05277e6c8bc14c --- /dev/null +++ b/model-00056-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d41f26faa4670d00a6b3d85ea0968447d0c40fc676adf6e4666bd592f048b2 +size 4362274144 diff --git a/model-00057-of-00201.safetensors b/model-00057-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd09ed631ed896acfe954d0b1e5a71f7f87b41d3 --- /dev/null +++ b/model-00057-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52af0d1ae3d70ca332c8f8b294c00fe25d64741d808f5dce683501cd3f16797f +size 4697621168 diff --git a/model-00058-of-00201.safetensors b/model-00058-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c5a41663f8b8fd00c198d5f13cd56d61ea5d139 --- /dev/null +++ b/model-00058-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bffffcd9b8339ed05401adbc457241bee405f0d9178cdcfd78512c6d8bf4408 +size 4999677056 diff --git a/model-00059-of-00201.safetensors b/model-00059-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a32d9646f08299999ff3e2f7a9847326f23366e4 --- /dev/null +++ b/model-00059-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4165338a4b805dcd93935bc2d5649c51e49729c4161e8d2bda1ef9d4a9c8c8 +size 4999742480 diff --git a/model-00060-of-00201.safetensors b/model-00060-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..174fc96dde2bb1935977d48c0febad4bb4383b41 --- /dev/null +++ b/model-00060-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82ecba7536c775992e4d69a6dde3af7d89c7c018933bfa11cf72c6498933f158 +size 4697621168 diff --git a/model-00061-of-00201.safetensors b/model-00061-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4519447995c351944950ef6a10e63504cf54a338 --- /dev/null +++ b/model-00061-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146abe8ea65766a332a56b9b5a3cec78550133c7098bd440197584ab63b38996 +size 4362274144 diff --git a/model-00062-of-00201.safetensors b/model-00062-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b6dfbc5ac5e1f797c7a944d54b53b632cc83612c --- /dev/null +++ b/model-00062-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7d9be8a7c94f6a9c589e1adc6ad34667487ac007b7e739c3fba59b028a44f9d +size 4697621168 diff --git a/model-00063-of-00201.safetensors b/model-00063-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cea66929dc87ac21a13bae2c0273286335d31d05 --- /dev/null +++ b/model-00063-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff51cf8d650a2310edc2e668ac799bf2863580b55c9d518ead22d3a3103d43b7 +size 4999677056 diff --git a/model-00064-of-00201.safetensors b/model-00064-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f11daa1543b01f04e8e7b68dfc67eee1606bcd64 --- /dev/null +++ b/model-00064-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f5aacd09f0b5895f6e70adee71f747f3a0860bdb631c4a6cc6991952983a62e +size 4999742480 diff --git a/model-00065-of-00201.safetensors b/model-00065-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d24e6d669bb536ef9902f912fc0f1bd660cedbda --- /dev/null +++ b/model-00065-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a723147ec1364de5f5dff38b62052fc77dba7d076fa965fd34ef91a794a94954 +size 4697621168 diff --git a/model-00066-of-00201.safetensors b/model-00066-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..866c14524c9b6f369a530a21466c36d7554ad311 --- /dev/null +++ b/model-00066-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad5a5b8af5e523873c0ea244ba98f1492793287be725f27d955a349e69b1942f +size 4362274144 diff --git a/model-00067-of-00201.safetensors b/model-00067-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..267adbf780c0da6831fdb28d26d46fdeb4650149 --- /dev/null +++ b/model-00067-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efbb30a58a3b13489cc532e6e701ef7d7a276464f1569334c48b78de5a29a572 +size 4697621168 diff --git a/model-00068-of-00201.safetensors b/model-00068-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db47f42ef0a4cd4b52afa5249092f644daae381f --- /dev/null +++ b/model-00068-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5147f50f3f337765fc3bfd29dcbbd3e86dace3242f99e2ad224214ec80b342f +size 4999677056 diff --git a/model-00069-of-00201.safetensors b/model-00069-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..386fd2184f126a17bb9a7558bf794df81293a99b --- /dev/null +++ b/model-00069-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f2efa95d966afc455375c58f3c40d5aa52ae4977953c4a8e08937ffe999e25 +size 4999742480 diff --git a/model-00070-of-00201.safetensors b/model-00070-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de65cd8ac45f64f9ced82f2ef989348fc9e1b840 --- /dev/null +++ b/model-00070-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:351ae97daeef2e4e8726272d4c9f961f3516e2e67bc4a879f4fa464d3f6075b7 +size 4697621168 diff --git a/model-00071-of-00201.safetensors b/model-00071-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..60cd8e64e4c7cdf1e5bc8bfa68d19630ce07ab03 --- /dev/null +++ b/model-00071-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e45653f8b1ae2c879f9b809d89a30b3fb42dc435b83224fdd4dcbce58720c2c +size 4362274144 diff --git a/model-00072-of-00201.safetensors b/model-00072-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7da723cea5e6d39cb090fa7db2fdcab08f50960 --- /dev/null +++ b/model-00072-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f77160c18560f621a0a280565964a48f7c88b7285b47e6dd6fb37a9293917dff +size 4697621168 diff --git a/model-00073-of-00201.safetensors b/model-00073-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..433488c7e538af8526165d32083ef31f548d4c96 --- /dev/null +++ b/model-00073-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63797645c3fad6da5b95060fd70339b5da1b3627d97bc133a4ce409a1037e51b +size 4999677056 diff --git a/model-00074-of-00201.safetensors b/model-00074-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91b94e9d55824fcc49e062298d684b6d9f31d986 --- /dev/null +++ b/model-00074-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806370de56212447ae41c7331220bcdefabfdc9639e78430d49b82ad6320d427 +size 4999742480 diff --git a/model-00075-of-00201.safetensors b/model-00075-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a8d1db8094ede4ce6dc6e3199978d10f93d0432 --- /dev/null +++ b/model-00075-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a395dfb55226b27dc7f3bf3ce0921575f4d4a740f1b1f7e1784f1d2e23b86b +size 4697621168 diff --git a/model-00076-of-00201.safetensors b/model-00076-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..601cbff6fb2b5b9371dd20b4a974e7a3e4fb1ab9 --- /dev/null +++ b/model-00076-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2baab5b0fa86ee4a6db0751da1232b04bf29b1cb1758db6a11d0e79df162e1af +size 4362274144 diff --git a/model-00077-of-00201.safetensors b/model-00077-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be8cfd0818cca66d4676cc4f312dadd5c23fbf60 --- /dev/null +++ b/model-00077-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dafc76b7ff02a498d53e9f568054a76d94b79c8768ff5821842754e2cb8608f +size 4697621168 diff --git a/model-00078-of-00201.safetensors b/model-00078-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7aa0281ab977b1a4359538b9b66d7105048acac --- /dev/null +++ b/model-00078-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0553bea3d589bfebb8a9ceb75aeb20fcd07421a2c1263e205549cf9733ba2b +size 4999677056 diff --git a/model-00079-of-00201.safetensors b/model-00079-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e235dc54c21bb876d5651a8f4047932361420597 --- /dev/null +++ b/model-00079-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e27c5afb8e125c383580dd829c8ca1d92ff6d1a42b2fa9b3f7bf26030407dfb5 +size 4999742480 diff --git a/model-00080-of-00201.safetensors b/model-00080-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db55b6703957efc4a684007115b8971465dc18af --- /dev/null +++ b/model-00080-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42ea01ff0d064cb0b23519579f1db5b4666e14350b4ef585c5bd60931bed06f3 +size 4697621168 diff --git a/model-00081-of-00201.safetensors b/model-00081-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56147ee5dd982998223ed9689039cfa2048d7323 --- /dev/null +++ b/model-00081-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41fad41916b67d2002a610b3acd160fcdf453f308243b931e65311482d6247b1 +size 4362274144 diff --git a/model-00082-of-00201.safetensors b/model-00082-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a66395f90dee9e4665e9b16c089e7510a048ce7 --- /dev/null +++ b/model-00082-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb6d04fafbfe836cf651278b0e3648e0aea4da692da37c73b236947f877793d +size 4697621168 diff --git a/model-00083-of-00201.safetensors b/model-00083-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a96a0a50bded07414b48a8a7f2513b57e00d32d2 --- /dev/null +++ b/model-00083-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd2477e7fb29589d0631ebbdd5be276f35e7fabefe20b2e6ba33faeb6c8b9976 +size 4999677056 diff --git a/model-00084-of-00201.safetensors b/model-00084-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5032536c7b9ee17df12f259cc047e7000200fc1 --- /dev/null +++ b/model-00084-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a6e6f1f8fb16eb0a301e59bd0371d611635cd0502e746f7ba5bd54835f34236 +size 4999742480 diff --git a/model-00085-of-00201.safetensors b/model-00085-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e94e6c9714a3f1cfafa58dccd44f9c132fbd354b --- /dev/null +++ b/model-00085-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f033a4b42c9bc037ccaf8cff965e2218c0cea001f511f5ef75ebad544f921d4 +size 4697621168 diff --git a/model-00086-of-00201.safetensors b/model-00086-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8476fa3f7892487fdc5519753daadf5c5b20274a --- /dev/null +++ b/model-00086-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:696c486f241b4032c99e3bf4529ba3a549591f19347fd3a5660839471c221369 +size 4362274144 diff --git a/model-00087-of-00201.safetensors b/model-00087-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6134654f66a652f7e20f50c13093afde8acb316c --- /dev/null +++ b/model-00087-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1a25f452e58e000c18155c2c235c73acf0e2ca95d4b16aa0819df9c35773ae4 +size 4697621168 diff --git a/model-00088-of-00201.safetensors b/model-00088-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a53191953869b60b6bcb900405239041793cd098 --- /dev/null +++ b/model-00088-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2659512dba09948d3e5f56fb6e75b0e3513ec67a12eb569833311ec9b8c379cd +size 4999677056 diff --git a/model-00089-of-00201.safetensors b/model-00089-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4418e36326576487a68061b95d09e9cc620c1351 --- /dev/null +++ b/model-00089-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ae5b709aafe746eb17add262699523f3a4d528a0235b1b4f3c1ceece9ef049 +size 4999742480 diff --git a/model-00090-of-00201.safetensors b/model-00090-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c23338b1d7b1f273282243fb8f06417bda9d30f9 --- /dev/null +++ b/model-00090-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51576c5b974b43bb5f175244155c59b7c42f6097c32cf5ad3d524f1d61023974 +size 4697621168 diff --git a/model-00091-of-00201.safetensors b/model-00091-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..746c8c9d060fa9302d87f4f9d2444935194accab --- /dev/null +++ b/model-00091-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a606084fa5f855bd0e68c12bcae917407c859fed90242303f913d1c71c18c5be +size 4362274144 diff --git a/model-00092-of-00201.safetensors b/model-00092-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..621630b84d6dbe85842b4ea09b45e21160b4d67c --- /dev/null +++ b/model-00092-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367933a84530b7e3c1db8941a153814a1c243ad79d06ddfe2b70054ca13bd9be +size 4697621168 diff --git a/model-00093-of-00201.safetensors b/model-00093-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c701928ed7a7e483b759b9275b4f26e62ec4e9df --- /dev/null +++ b/model-00093-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0044621eb4dceeb5f13b469b5bafa36e667f769cb6153b08ba736214127a30d3 +size 4999677056 diff --git a/model-00094-of-00201.safetensors b/model-00094-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..52bb341df40ee83c62a9e5733653fed474f3d95b --- /dev/null +++ b/model-00094-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5516789e72b14d88649df5dd551d3733f9fbcbd5d3826a72abb2aca923788607 +size 4999742480 diff --git a/model-00095-of-00201.safetensors b/model-00095-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..916fd6ab9094ecc7d0b87643614c709b9b479c10 --- /dev/null +++ b/model-00095-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125e2359c44117d556bc3066aa1b3e32f6c7782f417cfd9eeec22c6b1868141c +size 4697621168 diff --git a/model-00096-of-00201.safetensors b/model-00096-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b18d50fbf49ded476ef6376b9bdc8a0653effc3 --- /dev/null +++ b/model-00096-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e66caab7693dd19b217df0d9fd776c92ec8c4c8bf730e309408c265cdaccac8 +size 4362274144 diff --git a/model-00097-of-00201.safetensors b/model-00097-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5b9c92c6a6e748376a3ad77098d568b434b42a35 --- /dev/null +++ b/model-00097-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6fc0311b6c98486aa54ed1a257f13236b819a9fce10bc602a0c631f6658cc1a +size 4697621168 diff --git a/model-00098-of-00201.safetensors b/model-00098-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc87f156d43832accff4b3943340de083a24de6c --- /dev/null +++ b/model-00098-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a16ee6c1987cc13b18f4f7f76b5175839ac24b5153ae5e3706f9d00083354e00 +size 4999677056 diff --git a/model-00099-of-00201.safetensors b/model-00099-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b25f5bde555660fb33781adc0623c095eba7ea10 --- /dev/null +++ b/model-00099-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f90d6b2a0c11c68786bbff9916a9623854c75876940f246fa82f3c0c3b77d0f +size 4999742480 diff --git a/model-00100-of-00201.safetensors b/model-00100-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd403a7dcf55c5586e96a745356e100711a7f760 --- /dev/null +++ b/model-00100-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2259d272f7fa08573dba30d1bbb1fbc904483760fa65ad0bf55ec7a0eb97e89 +size 4697621168 diff --git a/model-00101-of-00201.safetensors b/model-00101-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12d037db2cab2451443d069a95a56ee6f3330e63 --- /dev/null +++ b/model-00101-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7db4fe71ccb02cb641c4248b2a33e2a8f747fe4ad5c721761fc6f75b718f104 +size 4362274144 diff --git a/model-00102-of-00201.safetensors b/model-00102-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c4eb6cc2581c56b7909384b7844975e34c9dfd53 --- /dev/null +++ b/model-00102-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:572a90103bd8e3943e8238c9593208e6ce840caf1edb728785479920cc08268b +size 4697621168 diff --git a/model-00103-of-00201.safetensors b/model-00103-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2302b767786de479d441a4b30511d096454c389a --- /dev/null +++ b/model-00103-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d1c98884136adc99713d6fa9564935deffde704514148a64d0490a0e42e60b5 +size 4999677056 diff --git a/model-00104-of-00201.safetensors b/model-00104-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e37d694d2e8fc8d0e43a804a30a2f483af68f378 --- /dev/null +++ b/model-00104-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c97901714c73f332e82042deab54afa1d855a5052bf8c150995c58d33b3ca1 +size 4999742480 diff --git a/model-00105-of-00201.safetensors b/model-00105-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..128a1347e1f3956aae0f3357371f793b668ba56f --- /dev/null +++ b/model-00105-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9df2299ed96bca531de83a0c4b50476da8f0efb050d8958300d0661731b0893 +size 4697621168 diff --git a/model-00106-of-00201.safetensors b/model-00106-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9ed9039d56f92e6ecc8fc5208df097b369fe3b3 --- /dev/null +++ b/model-00106-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af1a05040c71ba5033b9fb986af5d335d3dd9a9a67efd6cafecf26c1eabc04b +size 4362274144 diff --git a/model-00107-of-00201.safetensors b/model-00107-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21a806979f85068d0d048ea12352f42eae60d66d --- /dev/null +++ b/model-00107-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbe04da00aba05ba67a3693d737824bfa7f5b6480839f9df513a7df21a9072c2 +size 4697621168 diff --git a/model-00108-of-00201.safetensors b/model-00108-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b864de78163e3a7f361720668cd82faaf9df1ad --- /dev/null +++ b/model-00108-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c210390f9bacfa639bd341db2007ded48d3c3a3cf8099ee73a39f570deed75b +size 4999677056 diff --git a/model-00109-of-00201.safetensors b/model-00109-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..860bf14507a49f41363d719ca8d75b3e4a6118e5 --- /dev/null +++ b/model-00109-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00676fb292e3e371ab7d41057e75a6366dbc0866e7379813528ed41c09bdc889 +size 4999742480 diff --git a/model-00110-of-00201.safetensors b/model-00110-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64db6dcb6e39487ed764fe9d3a69d0a2d37d2dd0 --- /dev/null +++ b/model-00110-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb8d8b009b8b8507e59fd21a1d562fca8cda71972bcd1f9e31bc755c1d62ef6 +size 4697621168 diff --git a/model-00111-of-00201.safetensors b/model-00111-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..57fc1ac81db3cd9d024677fa7159cece1b7bde70 --- /dev/null +++ b/model-00111-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae84c5b3998527a12ab790084e7b51830925b84e0c86a17b1164aaa04d8e9ed +size 4362274144 diff --git a/model-00112-of-00201.safetensors b/model-00112-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1bd7845179a2fc9bd0f353bc708133a38480b70 --- /dev/null +++ b/model-00112-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7850b784144837228c995ffc42d220ea71c1e39b4628de682a4b88ec4dc062f +size 4697621168 diff --git a/model-00113-of-00201.safetensors b/model-00113-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..827b2ebd91ebb47ec47900c5bc920bf13e1ed7ab --- /dev/null +++ b/model-00113-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece027ca66a48335af5e9e7a3a44fe59cb00729b5d2cf7740274454381937da3 +size 4999677056 diff --git a/model-00114-of-00201.safetensors b/model-00114-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db30c4cfde4cad1c6b6d7d979fd38f006b0f55f5 --- /dev/null +++ b/model-00114-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:726c183289dfc03ccb0a37e77dcfa20f830f402d9f8fc3365aad30f42c9d11fc +size 4999742480 diff --git a/model-00115-of-00201.safetensors b/model-00115-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e80cb0d4e369767b07213361bcce3e2191c5e9dc --- /dev/null +++ b/model-00115-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a836f446f6403d3638ddf524bf691b49f1be55fb9acedc01f46288eba25ab2ce +size 4697621168 diff --git a/model-00116-of-00201.safetensors b/model-00116-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58b084931df303c15b8ae9d81947bc2308a89bde --- /dev/null +++ b/model-00116-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571220b1f52c676e3e8c56fe2f19bcf35889d0c0caff36187b18a8e51b2f5f71 +size 4362274144 diff --git a/model-00117-of-00201.safetensors b/model-00117-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..428a2e76df8604cc68869f750b6d5a32c8aa9f36 --- /dev/null +++ b/model-00117-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73e3c41980a51e03e989c37969a1f1bda381cf3e45b9a74f93d1b5f7446e8ff +size 4697621168 diff --git a/model-00118-of-00201.safetensors b/model-00118-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d62afba946ac1f139c4ceb6808ed14a2fc4da86e --- /dev/null +++ b/model-00118-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:385857d8abd145366dbfe8717a5b6d344923439b3fc4a0b5b283d33873be3088 +size 4999677056 diff --git a/model-00119-of-00201.safetensors b/model-00119-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82f92c2ffeabbbcd4e5a0827c38e72303c0960cd --- /dev/null +++ b/model-00119-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a4bc00a8e926570132d18662e195ba35ef5e7567a0458aaff83161fa87aceb1 +size 4999742480 diff --git a/model-00120-of-00201.safetensors b/model-00120-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ba1b84f6ced2510995cbf4ccc35a5280de6a2188 --- /dev/null +++ b/model-00120-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc459abe705f79344725b236eb6d8dc912b3b823193f0b4b0d22151526e3c220 +size 4697621168 diff --git a/model-00121-of-00201.safetensors b/model-00121-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..920381c4095a7f86c9bbaf5bcc86621bac247014 --- /dev/null +++ b/model-00121-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e922b1bdd1ad07aae5564554e73422ebeb14cb8703a7e91653fb45fefc1768e5 +size 4362274144 diff --git a/model-00122-of-00201.safetensors b/model-00122-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b0a25da6ea93df69f2fa81e28333d1c83a78fbed --- /dev/null +++ b/model-00122-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011028be13c336c49759246481acfaff81bb87eb1c6609fe4ca799f4a8d7a600 +size 4697621168 diff --git a/model-00123-of-00201.safetensors b/model-00123-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b91425201048f3ecbcedfdec97ff35af98bbbf78 --- /dev/null +++ b/model-00123-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e66af3b64394453312dd985a0ccd28596db7c0491e787909f360922a1f3b2a +size 4999677056 diff --git a/model-00124-of-00201.safetensors b/model-00124-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6cb5275ab1068aef63bb872045bf9accd9a00bfa --- /dev/null +++ b/model-00124-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8256e9d002cffec3d6ed7ed758773cdef3681dc279f451e73895b8a427336e5e +size 4999742480 diff --git a/model-00125-of-00201.safetensors b/model-00125-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35a9e16d93a1e7cd854444d1faceb4e6945a2b7e --- /dev/null +++ b/model-00125-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:292071d4a114d6d56ef3d79a8fcbff0beba3d5566b3ff3e47a1f9547cfd633ae +size 4697621168 diff --git a/model-00126-of-00201.safetensors b/model-00126-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6836e265f1686e15c3995a385a6d6e363d578017 --- /dev/null +++ b/model-00126-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56df530ef5c15e755e7a6a136833af7b652bcf4b0f2109667c6ac3528d18ea91 +size 4362274144 diff --git a/model-00127-of-00201.safetensors b/model-00127-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3dc4372b794d830fefcfb5220ab913ed89637733 --- /dev/null +++ b/model-00127-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85f4af221e70178f4e05f9701a97466421fb08e77a35ae7b967aa552830fd7c4 +size 4697621168 diff --git a/model-00128-of-00201.safetensors b/model-00128-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a894d1e968148b7587224dce538dd8e492dd216a --- /dev/null +++ b/model-00128-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25acc6cebc7cc0be5bc0019e9855abbbcd3c9c79bbe9b5f158126bd232e881cb +size 4999677056 diff --git a/model-00129-of-00201.safetensors b/model-00129-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d040f6d0cb8edad1ecfb1a3d734b5e08f83c46d9 --- /dev/null +++ b/model-00129-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0b3e15f623caf9b7172126c9054d4749bc5d829b2fe8d256b4992f398804f87 +size 4999742480 diff --git a/model-00130-of-00201.safetensors b/model-00130-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85a090a028fbd6a6343e239d3f96ea1d578004da --- /dev/null +++ b/model-00130-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0545106607b9dce2725d00f4d9cdea86693b7f270baf2ba588850fd12946375f +size 4697621168 diff --git a/model-00131-of-00201.safetensors b/model-00131-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c5af9f31174220909f5a0ee0e10b7cfbd2d7f56 --- /dev/null +++ b/model-00131-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa10f285ee7d1b7ce8f0e2dab362a6bf54253ed437e6846514c2013db65dbc2c +size 4362274144 diff --git a/model-00132-of-00201.safetensors b/model-00132-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b285d6302db4b992a751f609108eacc96ad349e2 --- /dev/null +++ b/model-00132-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16ac87364f039d71649930add71a937beded5f561d14be1bf99501079fef2aad +size 4697621168 diff --git a/model-00133-of-00201.safetensors b/model-00133-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8982fdae14b6110f382603a14b6e0ef78fa010dd --- /dev/null +++ b/model-00133-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074458d3df06c773156b7989eb15de41e86a44807c57e4ed97302adf0692b068 +size 4999677056 diff --git a/model-00134-of-00201.safetensors b/model-00134-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce07e19fafb9b6870033f153fa1e4a88021f528e --- /dev/null +++ b/model-00134-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf9f3732803ff93d966600720f2a456b380bd6fe9e7e8ec3ab4a0d554258574 +size 4999742480 diff --git a/model-00135-of-00201.safetensors b/model-00135-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fdff5aadcd483ed4b511c1dca8666209d1c5bc14 --- /dev/null +++ b/model-00135-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e484beb6d8c06e8c5d08d447d3dfa7ea22212beb4f3a4b1dbec3ba1917239a13 +size 4697621168 diff --git a/model-00136-of-00201.safetensors b/model-00136-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aff8b80107bce14733d7e8145a69edb3cec8d86f --- /dev/null +++ b/model-00136-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6eda06c384bf982718a838ba344c119d375d8b89e89c02c56b3e98bac3dd7ad +size 4362274144 diff --git a/model-00137-of-00201.safetensors b/model-00137-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f887e39593152ce4d45b25372b895f2bf7ebbe35 --- /dev/null +++ b/model-00137-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aeb243dacbbc45bfdb928227f26b719842f6d9385ec7752f8f0a146d96fcbce +size 4697621168 diff --git a/model-00138-of-00201.safetensors b/model-00138-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50d898e1591dce0b1ebe8333a665ec4dbefe58e3 --- /dev/null +++ b/model-00138-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67edac95991536d308d4fcf1ed32af46d1319471883c2b5c1a65c839ce0d863a +size 4999677056 diff --git a/model-00139-of-00201.safetensors b/model-00139-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d941e76b02e372ce35e0f2215d7460ca9326033 --- /dev/null +++ b/model-00139-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a19dab8cfed34ba0e43f63f82d43d60d85c6db5287b6d56947d94674588f43b +size 4999742480 diff --git a/model-00140-of-00201.safetensors b/model-00140-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..576102c708b73584f899878f06440b75784a6322 --- /dev/null +++ b/model-00140-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6baebfb6de1647c9a3c5adb2e3b879e9bf4d84d166379699fc7ff6c8906d308f +size 4697621168 diff --git a/model-00141-of-00201.safetensors b/model-00141-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cbdf39849b011d61d183ffd9f0344960fff90470 --- /dev/null +++ b/model-00141-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cf7feb7c0c535b071a96a2e993c7b4a8064b6ca4296ef077bc7a2c0c0ab92b +size 4362274144 diff --git a/model-00142-of-00201.safetensors b/model-00142-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d56a672106a5daff01abb36072a1c0ce8c8c387 --- /dev/null +++ b/model-00142-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19764fdd066a79c609beec4aca770a27d2c0552aa2ed1d3ac9b1bdec4246db3e +size 4697621168 diff --git a/model-00143-of-00201.safetensors b/model-00143-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07713b806b86af2569b854f010feecdf0b33fcf9 --- /dev/null +++ b/model-00143-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14555adf5a19a4a941c8b643bc2e46bd593bc55ee146986699652ecdc33d69a8 +size 4999677056 diff --git a/model-00144-of-00201.safetensors b/model-00144-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c45eb979aa566bdc6947d2a911d46a143dca464b --- /dev/null +++ b/model-00144-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d14c5d8fb959441ad4a4d730576a4a9a2f5e73de4dd00cbef5a55a753b0b631f +size 4999742480 diff --git a/model-00145-of-00201.safetensors b/model-00145-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e14c660d18ec5d38766287f2bcd2e175c07780c1 --- /dev/null +++ b/model-00145-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace85a78ff7772d6cc188160479ac86f2e17b688f81007b39b92fe78e9a4b532 +size 4697621168 diff --git a/model-00146-of-00201.safetensors b/model-00146-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f3c8e4d11c3ca73519b5ad23f17a879186015b58 --- /dev/null +++ b/model-00146-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96f6f16651d7a0737174f3ecac1e660e2d8ba4afd080032f107a751deed60f4 +size 4362274144 diff --git a/model-00147-of-00201.safetensors b/model-00147-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0e933281f8a7ff8de566651675140ed10e68c687 --- /dev/null +++ b/model-00147-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:689d32a86fc7a9dcf470ab63e1934c272394ec0874fbb3254cf7c8f42833f4e1 +size 4697621168 diff --git a/model-00148-of-00201.safetensors b/model-00148-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de0359a987a96c90c9d14840e2619138a0a4428a --- /dev/null +++ b/model-00148-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55dc519fcdcfe75ff32aba0426464785792147aa39cef8321cd784a6ceac20da +size 4999677056 diff --git a/model-00149-of-00201.safetensors b/model-00149-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ddc2eb54ce597a5322f20ca2714637eb7de3de5 --- /dev/null +++ b/model-00149-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0dbc85e281e6a21f859d8c3753cc76a5ec163d4d534fd86fd823c8d4a2162d3 +size 4999742480 diff --git a/model-00150-of-00201.safetensors b/model-00150-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d313050c02cf0b596e85dde22e1c858c54437d19 --- /dev/null +++ b/model-00150-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4c6c20481bd5bf0bfe723574e5d614b2d15312ac6c87306806c6b954406ee2 +size 4697621168 diff --git a/model-00151-of-00201.safetensors b/model-00151-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ebd0cf9f94d010a6e86156f546146854aed8960 --- /dev/null +++ b/model-00151-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3f1dfefe0cdb2cfd4aa57e7a33402a29da83830599ebc8922cbccf07f33d01 +size 4362274144 diff --git a/model-00152-of-00201.safetensors b/model-00152-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d76dc6b589357bf6ee910da322ce820a44e9efcf --- /dev/null +++ b/model-00152-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:369afec25f5aad965c273ba378cd489f6deca2b390abc0c392049d0ee58dcc51 +size 4697621168 diff --git a/model-00153-of-00201.safetensors b/model-00153-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33fd51d25ee4a113a7aa627be2009fd0045de6f5 --- /dev/null +++ b/model-00153-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf9567c9174ebd73a87eb1f34ec2c160cd4075c0457d2969b6b8a854f5f7c4a +size 4999677056 diff --git a/model-00154-of-00201.safetensors b/model-00154-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5245e20fce3481e281febd8af9d66fa4a160b9f --- /dev/null +++ b/model-00154-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae823dba8f7dfeceba5d13b0fac7b4ce45c9a2e48931b8c1ced86e432f56597 +size 4999742480 diff --git a/model-00155-of-00201.safetensors b/model-00155-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5bd6528a8943c63cd3062dd1f546aedd5f80efa --- /dev/null +++ b/model-00155-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:569d90c53760e87680653e36c9a73a050db48cd6e4cd0a018f147692d228e89b +size 4697621168 diff --git a/model-00156-of-00201.safetensors b/model-00156-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f81505d1d03527a50deb6ef79f44378262802132 --- /dev/null +++ b/model-00156-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d079994d10f837eb778f6842b26eea12d4fd2c1f8e322aa6f0dcd5cefb37eb79 +size 4362274144 diff --git a/model-00157-of-00201.safetensors b/model-00157-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b6585cf4b4316680546a1eab22a8f9a0288c6b6 --- /dev/null +++ b/model-00157-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b4cb149864cbe516711729b8c4d551ec91676624f349b05fca7ea7c86c0265 +size 4697621168 diff --git a/model-00158-of-00201.safetensors b/model-00158-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9fca476cd48f0bf893d67a8aa7b5132c24758f14 --- /dev/null +++ b/model-00158-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3760e56b976ad553d1b14c7e59c067c47cc93eb7de2a176de0ce40eadfc61f22 +size 4999677056 diff --git a/model-00159-of-00201.safetensors b/model-00159-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3332a2503dd6c6d2f8728f00604d4bf77de2ca3b --- /dev/null +++ b/model-00159-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af7dbfc6d46ed2a3b8b4b9249f58ecf09778abad8c9b8c1e022561238bf3fbe4 +size 4999742480 diff --git a/model-00160-of-00201.safetensors b/model-00160-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de27254d6b71d1340b51873718cbe36b1683f048 --- /dev/null +++ b/model-00160-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a90d29af8dedcbcb414d5791ff6acc6a0131665b1978258374175649ccf911d +size 4697621168 diff --git a/model-00161-of-00201.safetensors b/model-00161-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3539cf75dbdc5f9f7961391d6dd80fc8c44a8158 --- /dev/null +++ b/model-00161-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abba851a756e4a9ed3053ae1e7ce2a0c46e59f40a06d66f25cb5997e88d9de6d +size 4362274144 diff --git a/model-00162-of-00201.safetensors b/model-00162-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c14b31d4570e6af896b347596c78a4a7988f4b6 --- /dev/null +++ b/model-00162-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce16b82be8f59893b869f78c0d772108d1d9dd2d63331da616eb3f3260ba4f3 +size 4697621168 diff --git a/model-00163-of-00201.safetensors b/model-00163-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fd7ffd9d3dd9a2eb1d2c95d1b4d88e4f4e4c7308 --- /dev/null +++ b/model-00163-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd9dad77e0e6fb6c00f53c47e0299ecfab0f42c9f662f152095c02c9448d647e +size 4999677056 diff --git a/model-00164-of-00201.safetensors b/model-00164-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2aad801e125f5b7ec08451fc9300b6486ad0abc1 --- /dev/null +++ b/model-00164-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91e8f70035cdda9a0332abc459231a1d5062d5ce8495cc3052a07ebdf5415bfd +size 4999742480 diff --git a/model-00165-of-00201.safetensors b/model-00165-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5a2690f208b13fde52ab6721927f6c1c1dbbe79 --- /dev/null +++ b/model-00165-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1538eb6b69fd7e20db8aa0c77e19568b563515de7fc4c414d9409ae3fd6f5e09 +size 4697621168 diff --git a/model-00166-of-00201.safetensors b/model-00166-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91e952fdf893999ab6ba09847ee3eac5fb9cda2b --- /dev/null +++ b/model-00166-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9940f56a42a4b43c9fb66840219523b9cf813087ebb355bf01caeca2766f6e8c +size 4362274144 diff --git a/model-00167-of-00201.safetensors b/model-00167-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..019dcb138655cdc9bc8c035d02c8c95e80814d0a --- /dev/null +++ b/model-00167-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54984ae130006aee9ab842f586305f2b53b1c25b4bb2ed31ab7f0ed3dd887c17 +size 4697621168 diff --git a/model-00168-of-00201.safetensors b/model-00168-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c8408d3f7a317622d842f869421f861079465f6 --- /dev/null +++ b/model-00168-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0888e1e4a9c38dacebdfa27cd70959f7e2488fcaa28e50e4e0b5b9db6c3c5ca2 +size 4999677056 diff --git a/model-00169-of-00201.safetensors b/model-00169-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c437b7e8a6bcdf1ae7575a31a052e353420b2f93 --- /dev/null +++ b/model-00169-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa424e3ef9aa3fbbc098066dacd490e9dcc7c1d5ec33aa7c75b235017496d171 +size 4999742480 diff --git a/model-00170-of-00201.safetensors b/model-00170-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0dd402365ba52da222f0868dd2c2e7f7428bec03 --- /dev/null +++ b/model-00170-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93bfe5c9ea04577eed106887df976ddc939622de880d038eaff700615809bbf0 +size 4697621168 diff --git a/model-00171-of-00201.safetensors b/model-00171-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8aba58744e07be53c83480ccad171e7729abcba8 --- /dev/null +++ b/model-00171-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:477aa8d5f4de23121e02a1da1d32d880e9483e846914c5443e6a2a3f1b0542a7 +size 4362274144 diff --git a/model-00172-of-00201.safetensors b/model-00172-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e268bd5d192e49fe898e0bb8f0d9c672862de0c1 --- /dev/null +++ b/model-00172-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ea36931bee6c3b2370caa996df15393fd755c6aeb265416305d152d5cbfd62 +size 4697621168 diff --git a/model-00173-of-00201.safetensors b/model-00173-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b06b32fe97613d7e4f14378f22f383195bfeafc6 --- /dev/null +++ b/model-00173-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a273768e4b5131c2105d1528deecfc478ce6b11753d6860a846d7bdebb9022a +size 4999677056 diff --git a/model-00174-of-00201.safetensors b/model-00174-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b585a376ff4bbf6b934f16c1b9507d4aefc67b0 --- /dev/null +++ b/model-00174-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77df01ec63fbaaf351d3327fd84decaf7f500a133895b699107c69a0c9ea626b +size 4999742480 diff --git a/model-00175-of-00201.safetensors b/model-00175-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..451a7179efa268790c3cf60b0ecc2612ebc37d43 --- /dev/null +++ b/model-00175-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:292a7ee7689c6e447ebd7d0254fff5c2dd1180501aa085167f570f490460b622 +size 4697621168 diff --git a/model-00176-of-00201.safetensors b/model-00176-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..690758967582bfb9a573bddef45f1d7460dbb9a1 --- /dev/null +++ b/model-00176-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78703f038704610a4fa6c757fed5d170b208d2dcb84c05b5b32aea3d02490e4a +size 4362274144 diff --git a/model-00177-of-00201.safetensors b/model-00177-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a653f1c7de811212475bacd9a7c20932e4c976c6 --- /dev/null +++ b/model-00177-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73bf6227939d29021bdbff062d65612bce509124f816bf76b53af0a9bb031dbd +size 4697621168 diff --git a/model-00178-of-00201.safetensors b/model-00178-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f829932cb53cff48ed0553861c4bc3c28a3169c --- /dev/null +++ b/model-00178-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89028caf9fde4a8e53e25aae02e3b6c865434bb41240eb74bfe8d1d0fd2c5678 +size 4999677056 diff --git a/model-00179-of-00201.safetensors b/model-00179-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c79438a14b5be3aeda46b24e773cbd4134ed1043 --- /dev/null +++ b/model-00179-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d73c6322dcd858a207772302a590af94c9791f53cf0f7451c8cd8572b30445c +size 4999742480 diff --git a/model-00180-of-00201.safetensors b/model-00180-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fea751dc714824dd91a39b5acb0c64c343668323 --- /dev/null +++ b/model-00180-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc8b7e917ad70bf7ef52a9fae731714d3bc32618f1ba95486d78a6686dc184a +size 4697621168 diff --git a/model-00181-of-00201.safetensors b/model-00181-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e56c0509c795e45285567debeb148dfdce282e89 --- /dev/null +++ b/model-00181-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a1ea098e3a5ab54f583a3704c50f8945fadbbdb08179bf74c6c1f4c55f4cba +size 4362274144 diff --git a/model-00182-of-00201.safetensors b/model-00182-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..965de2b17707c239f443bbeed5a751b5d18a2f0b --- /dev/null +++ b/model-00182-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a10112ccaf0d5eee4ee09326f8a71bd8f6e4cfc29658327d3ca89c752ba8c0cc +size 4697621168 diff --git a/model-00183-of-00201.safetensors b/model-00183-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98c8feadd18944f8a6410d2a5d4bdf2bfb14d9a3 --- /dev/null +++ b/model-00183-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f2652de8606391b1b97f930ba3956f44437a28b2d673f49a2a17578a993d546 +size 4999677056 diff --git a/model-00184-of-00201.safetensors b/model-00184-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf6c151f5162b8284573862fa3454edf4369a8d6 --- /dev/null +++ b/model-00184-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9428d713f67594889c26161a5360bd2e80a88443fafe09d1417e1405a8461eca +size 4999742480 diff --git a/model-00185-of-00201.safetensors b/model-00185-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..055ff4e6a390c8accf31fedb802a33e5738edacf --- /dev/null +++ b/model-00185-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28b41d0e6964773d0d721e1dfd62d7f0d4cb93d7c6d8a5d6a8e66c99c3c68cb3 +size 4697621168 diff --git a/model-00186-of-00201.safetensors b/model-00186-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a2cb40e277d14e9d66e034a32e6f2f649c6ee6d --- /dev/null +++ b/model-00186-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d07747feb00f8e3fb89250c671f6a698be4ab2be02cc60759e3f031dcd3062f +size 4362274144 diff --git a/model-00187-of-00201.safetensors b/model-00187-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58e2f79d27d3ec68da7099363a740fea496e1353 --- /dev/null +++ b/model-00187-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ad1365816c8af2a27eba11c2512615e9bee8fd6e3ebb620c89a5b56cfeccb82 +size 4697621168 diff --git a/model-00188-of-00201.safetensors b/model-00188-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..568a089be6ad937b38e32c601f647cd86f88f7b0 --- /dev/null +++ b/model-00188-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc8840b0bc3781aacc8cbde2189c195662fe554a4c7910179ee283c074f4c1d +size 4999677056 diff --git a/model-00189-of-00201.safetensors b/model-00189-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..03cb22157813cc2ce3b82ef9b19d433ac8f779da --- /dev/null +++ b/model-00189-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:347a656d5909b67c77039d00aea3e551395da86ff5c98293366075c918b44564 +size 4999742480 diff --git a/model-00190-of-00201.safetensors b/model-00190-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad7f0891775fa58d62078e3be1e54ef8694e9054 --- /dev/null +++ b/model-00190-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e272455eb88c56f1f9a280a9a7307541bfadb0b9750aba90267c7eadf63212e +size 4697621168 diff --git a/model-00191-of-00201.safetensors b/model-00191-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4f146330fef18e1320a7a4bbdfc0fc03fb7177b --- /dev/null +++ b/model-00191-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f98793cb6dba3b11a9a616917c115b20e40b330a7cff96ec34cbd47ca3e0178 +size 4362274144 diff --git a/model-00192-of-00201.safetensors b/model-00192-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56811ebcbbc86eb346337fcd1ae2a50f5ee63b00 --- /dev/null +++ b/model-00192-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ebb669dc82fc36b246654aae21ea643a29f2bfdbddeb053ce608f1763e92a +size 4697621168 diff --git a/model-00193-of-00201.safetensors b/model-00193-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c554b46bc7c29cc9f1c1e48d738d6a15c7cd65a --- /dev/null +++ b/model-00193-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2cf7c9c287d189ace275a396942aca4dc080f755a9e04c7a754566c677babbb +size 4999677056 diff --git a/model-00194-of-00201.safetensors b/model-00194-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..910e7e41fe72b66084e170f9f6f03d0ea97be382 --- /dev/null +++ b/model-00194-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cfa3e1c5cfc9d6ae2e96bbbf78fe3f83789cf3519ad4da30a8c35b0bc35e9c4 +size 4999742480 diff --git a/model-00195-of-00201.safetensors b/model-00195-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9cb0838f0630bb8d61a2e09297ee2c538c8ffa9f --- /dev/null +++ b/model-00195-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ca2c7659542d33759981a4863d2e3fcd5ba39718a8ddc6c4feb435702ae5a85 +size 4697621168 diff --git a/model-00196-of-00201.safetensors b/model-00196-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5db9ac3429817960ae29734286a5ad64094079d4 --- /dev/null +++ b/model-00196-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5956af0077c1151c26eef7588e320b13c0d1c3bf852d63fb59d4f6c249a1db92 +size 4362274144 diff --git a/model-00197-of-00201.safetensors b/model-00197-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39ede2e1805979efeb5bda77b4525a2cabe25615 --- /dev/null +++ b/model-00197-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f34946e96577a8bececdf1d87183c477c3e1598ec8f583986b4574f6faa9c069 +size 4697621168 diff --git a/model-00198-of-00201.safetensors b/model-00198-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..467641a7c5a06c0bc473f14574d7c75e44db22cd --- /dev/null +++ b/model-00198-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2566b2e37ad0023dd100c13b93119d838775e2cf1941359d326277b73eedb837 +size 4999677056 diff --git a/model-00199-of-00201.safetensors b/model-00199-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55dcf34b8126c11610fec15fdf8aac46681d7baf --- /dev/null +++ b/model-00199-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4b7a6cb0b05d52d4ab63260095f823960074ca4ea653bd7c18fc4ab47e0c4ea +size 4999742480 diff --git a/model-00200-of-00201.safetensors b/model-00200-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c93168b071152d9fc6fa015acc70021b88a6de6 --- /dev/null +++ b/model-00200-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d3ab2f163baa4d80391ec32ca925ba6e66de6fe51c51e687b7dc698b71f2811 +size 4697621168 diff --git a/model-00201-of-00201.safetensors b/model-00201-of-00201.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..621d65db8dd4b9d530b04a21e01e0ca8a2f8070a --- /dev/null +++ b/model-00201-of-00201.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b8a4a54db8b4c24d67dfe7e09f4611016cb470f06f8c9096813822ae8b906f +size 2927723208 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..fb31a55f9f7f14d245c4bddf6afd7b1e3f4029a6 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1530 @@ +{ + "metadata": { + "total_size": 952374427648 + }, + "weight_map": { + "lm_head.weight": "model-00201-of-00201.safetensors", + "model.embed_tokens.weight": "model-00001-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00201.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00201.safetensors", + "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00201.safetensors", + "model.layers.0.input_layernorm.weight": "model-00003-of-00201.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00201.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00201.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00201.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00201.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00201.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00201.safetensors", + "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00201.safetensors", + "model.layers.1.input_layernorm.weight": "model-00006-of-00201.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00006-of-00201.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00201.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00201.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00201.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00028-of-00201.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00028-of-00201.safetensors", + "model.layers.10.block_sparse_moe.gate.weight": "model-00026-of-00201.safetensors", + "model.layers.10.input_layernorm.weight": "model-00028-of-00201.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00028-of-00201.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00026-of-00201.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00026-of-00201.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00026-of-00201.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00026-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00201.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00201.safetensors", + "model.layers.11.block_sparse_moe.gate.weight": "model-00029-of-00201.safetensors", + "model.layers.11.input_layernorm.weight": "model-00031-of-00201.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00031-of-00201.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00028-of-00201.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00029-of-00201.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00028-of-00201.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00029-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00201.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00201.safetensors", + "model.layers.12.block_sparse_moe.gate.weight": "model-00031-of-00201.safetensors", + "model.layers.12.input_layernorm.weight": "model-00033-of-00201.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00033-of-00201.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00031-of-00201.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00031-of-00201.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00031-of-00201.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00031-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00035-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00201.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00201.safetensors", + "model.layers.13.block_sparse_moe.gate.weight": "model-00034-of-00201.safetensors", + "model.layers.13.input_layernorm.weight": "model-00036-of-00201.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00036-of-00201.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00033-of-00201.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00034-of-00201.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00033-of-00201.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00034-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00201.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00201.safetensors", + "model.layers.14.block_sparse_moe.gate.weight": "model-00036-of-00201.safetensors", + "model.layers.14.input_layernorm.weight": "model-00038-of-00201.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00038-of-00201.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00036-of-00201.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00036-of-00201.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00036-of-00201.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00036-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00039-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00039-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00039-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00039-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00039-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00040-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00040-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00040-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00041-of-00201.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00041-of-00201.safetensors", + "model.layers.15.block_sparse_moe.gate.weight": "model-00039-of-00201.safetensors", + "model.layers.15.input_layernorm.weight": "model-00041-of-00201.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00041-of-00201.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00038-of-00201.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00039-of-00201.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00038-of-00201.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00039-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00041-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00041-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00042-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00042-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00042-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00042-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00042-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00043-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00043-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00201.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00201.safetensors", + "model.layers.16.block_sparse_moe.gate.weight": "model-00041-of-00201.safetensors", + "model.layers.16.input_layernorm.weight": "model-00043-of-00201.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00043-of-00201.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00041-of-00201.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00041-of-00201.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00041-of-00201.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00041-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00044-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00044-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00044-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00044-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00044-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00045-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00045-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00045-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00045-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00045-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00046-of-00201.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00046-of-00201.safetensors", + "model.layers.17.block_sparse_moe.gate.weight": "model-00044-of-00201.safetensors", + "model.layers.17.input_layernorm.weight": "model-00046-of-00201.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00046-of-00201.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00043-of-00201.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00044-of-00201.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00043-of-00201.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00044-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00046-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00046-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00047-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00047-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00047-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00047-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00047-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00048-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00048-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00048-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00048-of-00201.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00048-of-00201.safetensors", + "model.layers.18.block_sparse_moe.gate.weight": "model-00046-of-00201.safetensors", + "model.layers.18.input_layernorm.weight": "model-00048-of-00201.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00048-of-00201.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00046-of-00201.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00046-of-00201.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00046-of-00201.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00046-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00049-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00049-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00049-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00049-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00049-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00050-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00050-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00050-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00050-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00050-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00051-of-00201.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00051-of-00201.safetensors", + "model.layers.19.block_sparse_moe.gate.weight": "model-00049-of-00201.safetensors", + "model.layers.19.input_layernorm.weight": "model-00051-of-00201.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00051-of-00201.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00048-of-00201.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00049-of-00201.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00048-of-00201.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00049-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00201.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00201.safetensors", + "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00201.safetensors", + "model.layers.2.input_layernorm.weight": "model-00008-of-00201.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00201.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00201.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00201.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00201.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00051-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00051-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00052-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00052-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00052-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00052-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00052-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00053-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00053-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00053-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00053-of-00201.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00053-of-00201.safetensors", + "model.layers.20.block_sparse_moe.gate.weight": "model-00051-of-00201.safetensors", + "model.layers.20.input_layernorm.weight": "model-00053-of-00201.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00053-of-00201.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00051-of-00201.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00051-of-00201.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00051-of-00201.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00051-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00054-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00054-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00054-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00054-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00054-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00055-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00055-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00055-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00055-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00055-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00056-of-00201.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00056-of-00201.safetensors", + "model.layers.21.block_sparse_moe.gate.weight": "model-00054-of-00201.safetensors", + "model.layers.21.input_layernorm.weight": "model-00056-of-00201.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00056-of-00201.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00053-of-00201.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00054-of-00201.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00053-of-00201.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00054-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00056-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00056-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00057-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00057-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00057-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00057-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00057-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00058-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00058-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00058-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00058-of-00201.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00058-of-00201.safetensors", + "model.layers.22.block_sparse_moe.gate.weight": "model-00056-of-00201.safetensors", + "model.layers.22.input_layernorm.weight": "model-00058-of-00201.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00058-of-00201.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00056-of-00201.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00056-of-00201.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00056-of-00201.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00056-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00059-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00059-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00059-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00059-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00059-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00060-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00060-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00060-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00060-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00060-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00061-of-00201.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00061-of-00201.safetensors", + "model.layers.23.block_sparse_moe.gate.weight": "model-00059-of-00201.safetensors", + "model.layers.23.input_layernorm.weight": "model-00061-of-00201.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00061-of-00201.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00058-of-00201.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00059-of-00201.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00058-of-00201.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00059-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00061-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00061-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00062-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00062-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00062-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00062-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00062-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00063-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00063-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00063-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00063-of-00201.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00063-of-00201.safetensors", + "model.layers.24.block_sparse_moe.gate.weight": "model-00061-of-00201.safetensors", + "model.layers.24.input_layernorm.weight": "model-00063-of-00201.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00063-of-00201.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00061-of-00201.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00061-of-00201.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00061-of-00201.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00061-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00064-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00064-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00064-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00064-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00064-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00065-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00065-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00065-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00065-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00065-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00066-of-00201.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00066-of-00201.safetensors", + "model.layers.25.block_sparse_moe.gate.weight": "model-00064-of-00201.safetensors", + "model.layers.25.input_layernorm.weight": "model-00066-of-00201.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00066-of-00201.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00063-of-00201.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00064-of-00201.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00063-of-00201.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00064-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00066-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00066-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00067-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00067-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00067-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00067-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00067-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00068-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00068-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00068-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00068-of-00201.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00068-of-00201.safetensors", + "model.layers.26.block_sparse_moe.gate.weight": "model-00066-of-00201.safetensors", + "model.layers.26.input_layernorm.weight": "model-00068-of-00201.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00068-of-00201.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00066-of-00201.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00066-of-00201.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00066-of-00201.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00066-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00069-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00069-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00069-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00069-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00069-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00070-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00070-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00070-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00070-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00070-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00071-of-00201.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00071-of-00201.safetensors", + "model.layers.27.block_sparse_moe.gate.weight": "model-00069-of-00201.safetensors", + "model.layers.27.input_layernorm.weight": "model-00071-of-00201.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00071-of-00201.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00068-of-00201.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00069-of-00201.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00068-of-00201.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00069-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00071-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00071-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00072-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00072-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00072-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00072-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00072-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00073-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00073-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00073-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00073-of-00201.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00073-of-00201.safetensors", + "model.layers.28.block_sparse_moe.gate.weight": "model-00071-of-00201.safetensors", + "model.layers.28.input_layernorm.weight": "model-00073-of-00201.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00073-of-00201.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00071-of-00201.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00071-of-00201.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00071-of-00201.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00071-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00074-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00074-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00074-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00074-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00074-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00075-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00075-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00075-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00075-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00075-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00076-of-00201.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00076-of-00201.safetensors", + "model.layers.29.block_sparse_moe.gate.weight": "model-00074-of-00201.safetensors", + "model.layers.29.input_layernorm.weight": "model-00076-of-00201.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00076-of-00201.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00073-of-00201.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00074-of-00201.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00073-of-00201.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00074-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00201.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00201.safetensors", + "model.layers.3.block_sparse_moe.gate.weight": "model-00009-of-00201.safetensors", + "model.layers.3.input_layernorm.weight": "model-00011-of-00201.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00201.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00201.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00201.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00008-of-00201.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00076-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00076-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00077-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00077-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00077-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00077-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00077-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00078-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00078-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00078-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00078-of-00201.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00078-of-00201.safetensors", + "model.layers.30.block_sparse_moe.gate.weight": "model-00076-of-00201.safetensors", + "model.layers.30.input_layernorm.weight": "model-00078-of-00201.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00078-of-00201.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00076-of-00201.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00076-of-00201.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00076-of-00201.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00076-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00079-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00079-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00079-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00079-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00079-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00080-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00080-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00080-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00080-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00080-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00081-of-00201.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00081-of-00201.safetensors", + "model.layers.31.block_sparse_moe.gate.weight": "model-00079-of-00201.safetensors", + "model.layers.31.input_layernorm.weight": "model-00081-of-00201.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00081-of-00201.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00078-of-00201.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00079-of-00201.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00078-of-00201.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00079-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00081-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00081-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00082-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00082-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00082-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00082-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00082-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00083-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00083-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00083-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00083-of-00201.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00083-of-00201.safetensors", + "model.layers.32.block_sparse_moe.gate.weight": "model-00081-of-00201.safetensors", + "model.layers.32.input_layernorm.weight": "model-00083-of-00201.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00083-of-00201.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00081-of-00201.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00081-of-00201.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00081-of-00201.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00081-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00084-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00084-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00084-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00084-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00084-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00085-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00085-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00085-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00085-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00085-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00086-of-00201.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00086-of-00201.safetensors", + "model.layers.33.block_sparse_moe.gate.weight": "model-00084-of-00201.safetensors", + "model.layers.33.input_layernorm.weight": "model-00086-of-00201.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00086-of-00201.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00083-of-00201.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00084-of-00201.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00083-of-00201.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00084-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00086-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00086-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00087-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00087-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00087-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00087-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00087-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00088-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00088-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00088-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00088-of-00201.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00088-of-00201.safetensors", + "model.layers.34.block_sparse_moe.gate.weight": "model-00086-of-00201.safetensors", + "model.layers.34.input_layernorm.weight": "model-00088-of-00201.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00088-of-00201.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00086-of-00201.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00086-of-00201.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00086-of-00201.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00086-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00089-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00089-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00089-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00089-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00089-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00090-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00090-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00090-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00090-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00090-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00091-of-00201.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00091-of-00201.safetensors", + "model.layers.35.block_sparse_moe.gate.weight": "model-00089-of-00201.safetensors", + "model.layers.35.input_layernorm.weight": "model-00091-of-00201.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00091-of-00201.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00088-of-00201.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00089-of-00201.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00088-of-00201.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00089-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00091-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00091-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00092-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00092-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00092-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00092-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00092-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00093-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00093-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00093-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00093-of-00201.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00093-of-00201.safetensors", + "model.layers.36.block_sparse_moe.gate.weight": "model-00091-of-00201.safetensors", + "model.layers.36.input_layernorm.weight": "model-00093-of-00201.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00093-of-00201.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00091-of-00201.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00091-of-00201.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00091-of-00201.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00091-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00094-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00094-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00094-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00094-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00094-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00095-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00095-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00095-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00095-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00095-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00096-of-00201.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00096-of-00201.safetensors", + "model.layers.37.block_sparse_moe.gate.weight": "model-00094-of-00201.safetensors", + "model.layers.37.input_layernorm.weight": "model-00096-of-00201.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00096-of-00201.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00093-of-00201.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00094-of-00201.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00093-of-00201.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00094-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00096-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00096-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00097-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00097-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00097-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00097-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00097-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00098-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00098-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00098-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00098-of-00201.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00098-of-00201.safetensors", + "model.layers.38.block_sparse_moe.gate.weight": "model-00096-of-00201.safetensors", + "model.layers.38.input_layernorm.weight": "model-00098-of-00201.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00098-of-00201.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00096-of-00201.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00096-of-00201.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00096-of-00201.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00096-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00099-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00099-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00099-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00099-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00099-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00100-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00100-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00100-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00100-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00100-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00101-of-00201.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00101-of-00201.safetensors", + "model.layers.39.block_sparse_moe.gate.weight": "model-00099-of-00201.safetensors", + "model.layers.39.input_layernorm.weight": "model-00101-of-00201.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00101-of-00201.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00098-of-00201.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00099-of-00201.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00098-of-00201.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00099-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00201.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00201.safetensors", + "model.layers.4.block_sparse_moe.gate.weight": "model-00011-of-00201.safetensors", + "model.layers.4.input_layernorm.weight": "model-00013-of-00201.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00201.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00011-of-00201.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00011-of-00201.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00011-of-00201.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00011-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00101-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00101-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00102-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00102-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00102-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00102-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00102-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00103-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00103-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.3.w1.weight": "model-00103-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.3.w2.weight": "model-00103-of-00201.safetensors", + "model.layers.40.block_sparse_moe.experts.3.w3.weight": "model-00103-of-00201.safetensors", + "model.layers.40.block_sparse_moe.gate.weight": "model-00101-of-00201.safetensors", + "model.layers.40.input_layernorm.weight": "model-00103-of-00201.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00103-of-00201.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00101-of-00201.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00101-of-00201.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00101-of-00201.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00101-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00104-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00104-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00104-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00104-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00104-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00105-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00105-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00105-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00105-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.3.w1.weight": "model-00105-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.3.w2.weight": "model-00106-of-00201.safetensors", + "model.layers.41.block_sparse_moe.experts.3.w3.weight": "model-00106-of-00201.safetensors", + "model.layers.41.block_sparse_moe.gate.weight": "model-00104-of-00201.safetensors", + "model.layers.41.input_layernorm.weight": "model-00106-of-00201.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00106-of-00201.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00103-of-00201.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00104-of-00201.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00103-of-00201.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00104-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00106-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00106-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00107-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00107-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00107-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00107-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00107-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00108-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00108-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.3.w1.weight": "model-00108-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.3.w2.weight": "model-00108-of-00201.safetensors", + "model.layers.42.block_sparse_moe.experts.3.w3.weight": "model-00108-of-00201.safetensors", + "model.layers.42.block_sparse_moe.gate.weight": "model-00106-of-00201.safetensors", + "model.layers.42.input_layernorm.weight": "model-00108-of-00201.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00108-of-00201.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00106-of-00201.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00106-of-00201.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00106-of-00201.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00106-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00109-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00109-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00109-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00109-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00109-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00110-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00110-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00110-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00110-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.3.w1.weight": "model-00110-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.3.w2.weight": "model-00111-of-00201.safetensors", + "model.layers.43.block_sparse_moe.experts.3.w3.weight": "model-00111-of-00201.safetensors", + "model.layers.43.block_sparse_moe.gate.weight": "model-00109-of-00201.safetensors", + "model.layers.43.input_layernorm.weight": "model-00111-of-00201.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00111-of-00201.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00108-of-00201.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00109-of-00201.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00108-of-00201.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00109-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00111-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00111-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00112-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00112-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00112-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00112-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00112-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00113-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00113-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.3.w1.weight": "model-00113-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.3.w2.weight": "model-00113-of-00201.safetensors", + "model.layers.44.block_sparse_moe.experts.3.w3.weight": "model-00113-of-00201.safetensors", + "model.layers.44.block_sparse_moe.gate.weight": "model-00111-of-00201.safetensors", + "model.layers.44.input_layernorm.weight": "model-00113-of-00201.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00113-of-00201.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00111-of-00201.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00111-of-00201.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00111-of-00201.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00111-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00114-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00114-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00114-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00114-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00114-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00115-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00115-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00115-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00115-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.3.w1.weight": "model-00115-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.3.w2.weight": "model-00116-of-00201.safetensors", + "model.layers.45.block_sparse_moe.experts.3.w3.weight": "model-00116-of-00201.safetensors", + "model.layers.45.block_sparse_moe.gate.weight": "model-00114-of-00201.safetensors", + "model.layers.45.input_layernorm.weight": "model-00116-of-00201.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00116-of-00201.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00113-of-00201.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00114-of-00201.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00113-of-00201.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00114-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00116-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00116-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00117-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00117-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00117-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00117-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00117-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00118-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00118-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.3.w1.weight": "model-00118-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.3.w2.weight": "model-00118-of-00201.safetensors", + "model.layers.46.block_sparse_moe.experts.3.w3.weight": "model-00118-of-00201.safetensors", + "model.layers.46.block_sparse_moe.gate.weight": "model-00116-of-00201.safetensors", + "model.layers.46.input_layernorm.weight": "model-00118-of-00201.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00118-of-00201.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00116-of-00201.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00116-of-00201.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00116-of-00201.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00116-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00119-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00119-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00119-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00119-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00119-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00120-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00120-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00120-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00120-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.3.w1.weight": "model-00120-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.3.w2.weight": "model-00121-of-00201.safetensors", + "model.layers.47.block_sparse_moe.experts.3.w3.weight": "model-00121-of-00201.safetensors", + "model.layers.47.block_sparse_moe.gate.weight": "model-00119-of-00201.safetensors", + "model.layers.47.input_layernorm.weight": "model-00121-of-00201.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00121-of-00201.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00118-of-00201.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00119-of-00201.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00118-of-00201.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00119-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00121-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00121-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00122-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00122-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00122-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00122-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.2.w1.weight": "model-00122-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.2.w2.weight": "model-00123-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.2.w3.weight": "model-00123-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.3.w1.weight": "model-00123-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.3.w2.weight": "model-00123-of-00201.safetensors", + "model.layers.48.block_sparse_moe.experts.3.w3.weight": "model-00123-of-00201.safetensors", + "model.layers.48.block_sparse_moe.gate.weight": "model-00121-of-00201.safetensors", + "model.layers.48.input_layernorm.weight": "model-00123-of-00201.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00123-of-00201.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00121-of-00201.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00121-of-00201.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00121-of-00201.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00121-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00124-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00124-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00124-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00124-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00124-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00125-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.2.w1.weight": "model-00125-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.2.w2.weight": "model-00125-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.2.w3.weight": "model-00125-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.3.w1.weight": "model-00125-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.3.w2.weight": "model-00126-of-00201.safetensors", + "model.layers.49.block_sparse_moe.experts.3.w3.weight": "model-00126-of-00201.safetensors", + "model.layers.49.block_sparse_moe.gate.weight": "model-00124-of-00201.safetensors", + "model.layers.49.input_layernorm.weight": "model-00126-of-00201.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00126-of-00201.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00123-of-00201.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00124-of-00201.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00123-of-00201.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00124-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00201.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00201.safetensors", + "model.layers.5.block_sparse_moe.gate.weight": "model-00014-of-00201.safetensors", + "model.layers.5.input_layernorm.weight": "model-00016-of-00201.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00016-of-00201.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00201.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00014-of-00201.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00201.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00014-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00126-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00126-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00127-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00127-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00127-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00127-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.2.w1.weight": "model-00127-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.2.w2.weight": "model-00128-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.2.w3.weight": "model-00128-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.3.w1.weight": "model-00128-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.3.w2.weight": "model-00128-of-00201.safetensors", + "model.layers.50.block_sparse_moe.experts.3.w3.weight": "model-00128-of-00201.safetensors", + "model.layers.50.block_sparse_moe.gate.weight": "model-00126-of-00201.safetensors", + "model.layers.50.input_layernorm.weight": "model-00128-of-00201.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00128-of-00201.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00126-of-00201.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00126-of-00201.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00126-of-00201.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00126-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00129-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00129-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00129-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00129-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00129-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00130-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.2.w1.weight": "model-00130-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.2.w2.weight": "model-00130-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.2.w3.weight": "model-00130-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.3.w1.weight": "model-00130-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.3.w2.weight": "model-00131-of-00201.safetensors", + "model.layers.51.block_sparse_moe.experts.3.w3.weight": "model-00131-of-00201.safetensors", + "model.layers.51.block_sparse_moe.gate.weight": "model-00129-of-00201.safetensors", + "model.layers.51.input_layernorm.weight": "model-00131-of-00201.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00131-of-00201.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00128-of-00201.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00129-of-00201.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00128-of-00201.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00129-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00131-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00131-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00132-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00132-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00132-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00132-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.2.w1.weight": "model-00132-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.2.w2.weight": "model-00133-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.2.w3.weight": "model-00133-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.3.w1.weight": "model-00133-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.3.w2.weight": "model-00133-of-00201.safetensors", + "model.layers.52.block_sparse_moe.experts.3.w3.weight": "model-00133-of-00201.safetensors", + "model.layers.52.block_sparse_moe.gate.weight": "model-00131-of-00201.safetensors", + "model.layers.52.input_layernorm.weight": "model-00133-of-00201.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00133-of-00201.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00131-of-00201.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00131-of-00201.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00131-of-00201.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00131-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00134-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00134-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00134-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00134-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00134-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00135-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.2.w1.weight": "model-00135-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.2.w2.weight": "model-00135-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.2.w3.weight": "model-00135-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.3.w1.weight": "model-00135-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.3.w2.weight": "model-00136-of-00201.safetensors", + "model.layers.53.block_sparse_moe.experts.3.w3.weight": "model-00136-of-00201.safetensors", + "model.layers.53.block_sparse_moe.gate.weight": "model-00134-of-00201.safetensors", + "model.layers.53.input_layernorm.weight": "model-00136-of-00201.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00136-of-00201.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00133-of-00201.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00134-of-00201.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00133-of-00201.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00134-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00136-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00136-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00137-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00137-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00137-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00137-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.2.w1.weight": "model-00137-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.2.w2.weight": "model-00138-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.2.w3.weight": "model-00138-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.3.w1.weight": "model-00138-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.3.w2.weight": "model-00138-of-00201.safetensors", + "model.layers.54.block_sparse_moe.experts.3.w3.weight": "model-00138-of-00201.safetensors", + "model.layers.54.block_sparse_moe.gate.weight": "model-00136-of-00201.safetensors", + "model.layers.54.input_layernorm.weight": "model-00138-of-00201.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00138-of-00201.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00136-of-00201.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00136-of-00201.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00136-of-00201.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00136-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00139-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00139-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00139-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00139-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00139-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00140-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.2.w1.weight": "model-00140-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.2.w2.weight": "model-00140-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.2.w3.weight": "model-00140-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.3.w1.weight": "model-00140-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.3.w2.weight": "model-00141-of-00201.safetensors", + "model.layers.55.block_sparse_moe.experts.3.w3.weight": "model-00141-of-00201.safetensors", + "model.layers.55.block_sparse_moe.gate.weight": "model-00139-of-00201.safetensors", + "model.layers.55.input_layernorm.weight": "model-00141-of-00201.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00141-of-00201.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00138-of-00201.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00139-of-00201.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00138-of-00201.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00139-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00141-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00141-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00142-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00142-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00142-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00142-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.2.w1.weight": "model-00142-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.2.w2.weight": "model-00143-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.2.w3.weight": "model-00143-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.3.w1.weight": "model-00143-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.3.w2.weight": "model-00143-of-00201.safetensors", + "model.layers.56.block_sparse_moe.experts.3.w3.weight": "model-00143-of-00201.safetensors", + "model.layers.56.block_sparse_moe.gate.weight": "model-00141-of-00201.safetensors", + "model.layers.56.input_layernorm.weight": "model-00143-of-00201.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00143-of-00201.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00141-of-00201.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00141-of-00201.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00141-of-00201.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00141-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00144-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00144-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00144-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00144-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00144-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00145-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.2.w1.weight": "model-00145-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.2.w2.weight": "model-00145-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.2.w3.weight": "model-00145-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.3.w1.weight": "model-00145-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.3.w2.weight": "model-00146-of-00201.safetensors", + "model.layers.57.block_sparse_moe.experts.3.w3.weight": "model-00146-of-00201.safetensors", + "model.layers.57.block_sparse_moe.gate.weight": "model-00144-of-00201.safetensors", + "model.layers.57.input_layernorm.weight": "model-00146-of-00201.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00146-of-00201.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00143-of-00201.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00144-of-00201.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00143-of-00201.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00144-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00146-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00146-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00147-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00147-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00147-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00147-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.2.w1.weight": "model-00147-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.2.w2.weight": "model-00148-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.2.w3.weight": "model-00148-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.3.w1.weight": "model-00148-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.3.w2.weight": "model-00148-of-00201.safetensors", + "model.layers.58.block_sparse_moe.experts.3.w3.weight": "model-00148-of-00201.safetensors", + "model.layers.58.block_sparse_moe.gate.weight": "model-00146-of-00201.safetensors", + "model.layers.58.input_layernorm.weight": "model-00148-of-00201.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00148-of-00201.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00146-of-00201.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00146-of-00201.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00146-of-00201.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00146-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00149-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00149-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00149-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00149-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00149-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00150-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.2.w1.weight": "model-00150-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.2.w2.weight": "model-00150-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.2.w3.weight": "model-00150-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.3.w1.weight": "model-00150-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.3.w2.weight": "model-00151-of-00201.safetensors", + "model.layers.59.block_sparse_moe.experts.3.w3.weight": "model-00151-of-00201.safetensors", + "model.layers.59.block_sparse_moe.gate.weight": "model-00149-of-00201.safetensors", + "model.layers.59.input_layernorm.weight": "model-00151-of-00201.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00151-of-00201.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00148-of-00201.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00149-of-00201.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00148-of-00201.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00149-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00201.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00201.safetensors", + "model.layers.6.block_sparse_moe.gate.weight": "model-00016-of-00201.safetensors", + "model.layers.6.input_layernorm.weight": "model-00018-of-00201.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00201.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00016-of-00201.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00016-of-00201.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00016-of-00201.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00016-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.0.w1.weight": "model-00151-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.0.w2.weight": "model-00151-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.0.w3.weight": "model-00152-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.1.w1.weight": "model-00152-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.1.w2.weight": "model-00152-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.1.w3.weight": "model-00152-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.2.w1.weight": "model-00152-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.2.w2.weight": "model-00153-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.2.w3.weight": "model-00153-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.3.w1.weight": "model-00153-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.3.w2.weight": "model-00153-of-00201.safetensors", + "model.layers.60.block_sparse_moe.experts.3.w3.weight": "model-00153-of-00201.safetensors", + "model.layers.60.block_sparse_moe.gate.weight": "model-00151-of-00201.safetensors", + "model.layers.60.input_layernorm.weight": "model-00153-of-00201.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00153-of-00201.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00151-of-00201.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00151-of-00201.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00151-of-00201.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00151-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.0.w1.weight": "model-00154-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.0.w2.weight": "model-00154-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.0.w3.weight": "model-00154-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.1.w1.weight": "model-00154-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.1.w2.weight": "model-00154-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.1.w3.weight": "model-00155-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.2.w1.weight": "model-00155-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.2.w2.weight": "model-00155-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.2.w3.weight": "model-00155-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.3.w1.weight": "model-00155-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.3.w2.weight": "model-00156-of-00201.safetensors", + "model.layers.61.block_sparse_moe.experts.3.w3.weight": "model-00156-of-00201.safetensors", + "model.layers.61.block_sparse_moe.gate.weight": "model-00154-of-00201.safetensors", + "model.layers.61.input_layernorm.weight": "model-00156-of-00201.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00156-of-00201.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00153-of-00201.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00154-of-00201.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00153-of-00201.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00154-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.0.w1.weight": "model-00156-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.0.w2.weight": "model-00156-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.0.w3.weight": "model-00157-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.1.w1.weight": "model-00157-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.1.w2.weight": "model-00157-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.1.w3.weight": "model-00157-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.2.w1.weight": "model-00157-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.2.w2.weight": "model-00158-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.2.w3.weight": "model-00158-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.3.w1.weight": "model-00158-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.3.w2.weight": "model-00158-of-00201.safetensors", + "model.layers.62.block_sparse_moe.experts.3.w3.weight": "model-00158-of-00201.safetensors", + "model.layers.62.block_sparse_moe.gate.weight": "model-00156-of-00201.safetensors", + "model.layers.62.input_layernorm.weight": "model-00158-of-00201.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00158-of-00201.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00156-of-00201.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00156-of-00201.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00156-of-00201.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00156-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.0.w1.weight": "model-00159-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.0.w2.weight": "model-00159-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.0.w3.weight": "model-00159-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.1.w1.weight": "model-00159-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.1.w2.weight": "model-00159-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.1.w3.weight": "model-00160-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.2.w1.weight": "model-00160-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.2.w2.weight": "model-00160-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.2.w3.weight": "model-00160-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.3.w1.weight": "model-00160-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.3.w2.weight": "model-00161-of-00201.safetensors", + "model.layers.63.block_sparse_moe.experts.3.w3.weight": "model-00161-of-00201.safetensors", + "model.layers.63.block_sparse_moe.gate.weight": "model-00159-of-00201.safetensors", + "model.layers.63.input_layernorm.weight": "model-00161-of-00201.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00161-of-00201.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00158-of-00201.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00159-of-00201.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00158-of-00201.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00159-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.0.w1.weight": "model-00161-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.0.w2.weight": "model-00161-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.0.w3.weight": "model-00162-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.1.w1.weight": "model-00162-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.1.w2.weight": "model-00162-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.1.w3.weight": "model-00162-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.2.w1.weight": "model-00162-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.2.w2.weight": "model-00163-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.2.w3.weight": "model-00163-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.3.w1.weight": "model-00163-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.3.w2.weight": "model-00163-of-00201.safetensors", + "model.layers.64.block_sparse_moe.experts.3.w3.weight": "model-00163-of-00201.safetensors", + "model.layers.64.block_sparse_moe.gate.weight": "model-00161-of-00201.safetensors", + "model.layers.64.input_layernorm.weight": "model-00163-of-00201.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00163-of-00201.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00161-of-00201.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00161-of-00201.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00161-of-00201.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00161-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.0.w1.weight": "model-00164-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.0.w2.weight": "model-00164-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.0.w3.weight": "model-00164-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.1.w1.weight": "model-00164-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.1.w2.weight": "model-00164-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.1.w3.weight": "model-00165-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.2.w1.weight": "model-00165-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.2.w2.weight": "model-00165-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.2.w3.weight": "model-00165-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.3.w1.weight": "model-00165-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.3.w2.weight": "model-00166-of-00201.safetensors", + "model.layers.65.block_sparse_moe.experts.3.w3.weight": "model-00166-of-00201.safetensors", + "model.layers.65.block_sparse_moe.gate.weight": "model-00164-of-00201.safetensors", + "model.layers.65.input_layernorm.weight": "model-00166-of-00201.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00166-of-00201.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00163-of-00201.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00164-of-00201.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00163-of-00201.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00164-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.0.w1.weight": "model-00166-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.0.w2.weight": "model-00166-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.0.w3.weight": "model-00167-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.1.w1.weight": "model-00167-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.1.w2.weight": "model-00167-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.1.w3.weight": "model-00167-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.2.w1.weight": "model-00167-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.2.w2.weight": "model-00168-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.2.w3.weight": "model-00168-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.3.w1.weight": "model-00168-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.3.w2.weight": "model-00168-of-00201.safetensors", + "model.layers.66.block_sparse_moe.experts.3.w3.weight": "model-00168-of-00201.safetensors", + "model.layers.66.block_sparse_moe.gate.weight": "model-00166-of-00201.safetensors", + "model.layers.66.input_layernorm.weight": "model-00168-of-00201.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00168-of-00201.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00166-of-00201.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00166-of-00201.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00166-of-00201.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00166-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.0.w1.weight": "model-00169-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.0.w2.weight": "model-00169-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.0.w3.weight": "model-00169-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.1.w1.weight": "model-00169-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.1.w2.weight": "model-00169-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.1.w3.weight": "model-00170-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.2.w1.weight": "model-00170-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.2.w2.weight": "model-00170-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.2.w3.weight": "model-00170-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.3.w1.weight": "model-00170-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.3.w2.weight": "model-00171-of-00201.safetensors", + "model.layers.67.block_sparse_moe.experts.3.w3.weight": "model-00171-of-00201.safetensors", + "model.layers.67.block_sparse_moe.gate.weight": "model-00169-of-00201.safetensors", + "model.layers.67.input_layernorm.weight": "model-00171-of-00201.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00171-of-00201.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00168-of-00201.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00169-of-00201.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00168-of-00201.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00169-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.0.w1.weight": "model-00171-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.0.w2.weight": "model-00171-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.0.w3.weight": "model-00172-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.1.w1.weight": "model-00172-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.1.w2.weight": "model-00172-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.1.w3.weight": "model-00172-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.2.w1.weight": "model-00172-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.2.w2.weight": "model-00173-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.2.w3.weight": "model-00173-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.3.w1.weight": "model-00173-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.3.w2.weight": "model-00173-of-00201.safetensors", + "model.layers.68.block_sparse_moe.experts.3.w3.weight": "model-00173-of-00201.safetensors", + "model.layers.68.block_sparse_moe.gate.weight": "model-00171-of-00201.safetensors", + "model.layers.68.input_layernorm.weight": "model-00173-of-00201.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00173-of-00201.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00171-of-00201.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00171-of-00201.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00171-of-00201.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00171-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.0.w1.weight": "model-00174-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.0.w2.weight": "model-00174-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.0.w3.weight": "model-00174-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.1.w1.weight": "model-00174-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.1.w2.weight": "model-00174-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.1.w3.weight": "model-00175-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.2.w1.weight": "model-00175-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.2.w2.weight": "model-00175-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.2.w3.weight": "model-00175-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.3.w1.weight": "model-00175-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.3.w2.weight": "model-00176-of-00201.safetensors", + "model.layers.69.block_sparse_moe.experts.3.w3.weight": "model-00176-of-00201.safetensors", + "model.layers.69.block_sparse_moe.gate.weight": "model-00174-of-00201.safetensors", + "model.layers.69.input_layernorm.weight": "model-00176-of-00201.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00176-of-00201.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00173-of-00201.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00174-of-00201.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00173-of-00201.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00174-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00201.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00201.safetensors", + "model.layers.7.block_sparse_moe.gate.weight": "model-00019-of-00201.safetensors", + "model.layers.7.input_layernorm.weight": "model-00021-of-00201.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00201.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00018-of-00201.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00019-of-00201.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00201.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00019-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.0.w1.weight": "model-00176-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.0.w2.weight": "model-00176-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.0.w3.weight": "model-00177-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.1.w1.weight": "model-00177-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.1.w2.weight": "model-00177-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.1.w3.weight": "model-00177-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.2.w1.weight": "model-00177-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.2.w2.weight": "model-00178-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.2.w3.weight": "model-00178-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.3.w1.weight": "model-00178-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.3.w2.weight": "model-00178-of-00201.safetensors", + "model.layers.70.block_sparse_moe.experts.3.w3.weight": "model-00178-of-00201.safetensors", + "model.layers.70.block_sparse_moe.gate.weight": "model-00176-of-00201.safetensors", + "model.layers.70.input_layernorm.weight": "model-00178-of-00201.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00178-of-00201.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00176-of-00201.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00176-of-00201.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00176-of-00201.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00176-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.0.w1.weight": "model-00179-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.0.w2.weight": "model-00179-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.0.w3.weight": "model-00179-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.1.w1.weight": "model-00179-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.1.w2.weight": "model-00179-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.1.w3.weight": "model-00180-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.2.w1.weight": "model-00180-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.2.w2.weight": "model-00180-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.2.w3.weight": "model-00180-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.3.w1.weight": "model-00180-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.3.w2.weight": "model-00181-of-00201.safetensors", + "model.layers.71.block_sparse_moe.experts.3.w3.weight": "model-00181-of-00201.safetensors", + "model.layers.71.block_sparse_moe.gate.weight": "model-00179-of-00201.safetensors", + "model.layers.71.input_layernorm.weight": "model-00181-of-00201.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00181-of-00201.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00178-of-00201.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00179-of-00201.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00178-of-00201.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00179-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.0.w1.weight": "model-00181-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.0.w2.weight": "model-00181-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.0.w3.weight": "model-00182-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.1.w1.weight": "model-00182-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.1.w2.weight": "model-00182-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.1.w3.weight": "model-00182-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.2.w1.weight": "model-00182-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.2.w2.weight": "model-00183-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.2.w3.weight": "model-00183-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.3.w1.weight": "model-00183-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.3.w2.weight": "model-00183-of-00201.safetensors", + "model.layers.72.block_sparse_moe.experts.3.w3.weight": "model-00183-of-00201.safetensors", + "model.layers.72.block_sparse_moe.gate.weight": "model-00181-of-00201.safetensors", + "model.layers.72.input_layernorm.weight": "model-00183-of-00201.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00183-of-00201.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00181-of-00201.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00181-of-00201.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00181-of-00201.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00181-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.0.w1.weight": "model-00184-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.0.w2.weight": "model-00184-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.0.w3.weight": "model-00184-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.1.w1.weight": "model-00184-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.1.w2.weight": "model-00184-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.1.w3.weight": "model-00185-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.2.w1.weight": "model-00185-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.2.w2.weight": "model-00185-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.2.w3.weight": "model-00185-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.3.w1.weight": "model-00185-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.3.w2.weight": "model-00186-of-00201.safetensors", + "model.layers.73.block_sparse_moe.experts.3.w3.weight": "model-00186-of-00201.safetensors", + "model.layers.73.block_sparse_moe.gate.weight": "model-00184-of-00201.safetensors", + "model.layers.73.input_layernorm.weight": "model-00186-of-00201.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00186-of-00201.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00183-of-00201.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00184-of-00201.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00183-of-00201.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00184-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.0.w1.weight": "model-00186-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.0.w2.weight": "model-00186-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.0.w3.weight": "model-00187-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.1.w1.weight": "model-00187-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.1.w2.weight": "model-00187-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.1.w3.weight": "model-00187-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.2.w1.weight": "model-00187-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.2.w2.weight": "model-00188-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.2.w3.weight": "model-00188-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.3.w1.weight": "model-00188-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.3.w2.weight": "model-00188-of-00201.safetensors", + "model.layers.74.block_sparse_moe.experts.3.w3.weight": "model-00188-of-00201.safetensors", + "model.layers.74.block_sparse_moe.gate.weight": "model-00186-of-00201.safetensors", + "model.layers.74.input_layernorm.weight": "model-00188-of-00201.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00188-of-00201.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00186-of-00201.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00186-of-00201.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00186-of-00201.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00186-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.0.w1.weight": "model-00189-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.0.w2.weight": "model-00189-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.0.w3.weight": "model-00189-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.1.w1.weight": "model-00189-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.1.w2.weight": "model-00189-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.1.w3.weight": "model-00190-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.2.w1.weight": "model-00190-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.2.w2.weight": "model-00190-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.2.w3.weight": "model-00190-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.3.w1.weight": "model-00190-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.3.w2.weight": "model-00191-of-00201.safetensors", + "model.layers.75.block_sparse_moe.experts.3.w3.weight": "model-00191-of-00201.safetensors", + "model.layers.75.block_sparse_moe.gate.weight": "model-00189-of-00201.safetensors", + "model.layers.75.input_layernorm.weight": "model-00191-of-00201.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00191-of-00201.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00188-of-00201.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00189-of-00201.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00188-of-00201.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00189-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.0.w1.weight": "model-00191-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.0.w2.weight": "model-00191-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.0.w3.weight": "model-00192-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.1.w1.weight": "model-00192-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.1.w2.weight": "model-00192-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.1.w3.weight": "model-00192-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.2.w1.weight": "model-00192-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.2.w2.weight": "model-00193-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.2.w3.weight": "model-00193-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.3.w1.weight": "model-00193-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.3.w2.weight": "model-00193-of-00201.safetensors", + "model.layers.76.block_sparse_moe.experts.3.w3.weight": "model-00193-of-00201.safetensors", + "model.layers.76.block_sparse_moe.gate.weight": "model-00191-of-00201.safetensors", + "model.layers.76.input_layernorm.weight": "model-00193-of-00201.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00193-of-00201.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00191-of-00201.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00191-of-00201.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00191-of-00201.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00191-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.0.w1.weight": "model-00194-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.0.w2.weight": "model-00194-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.0.w3.weight": "model-00194-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.1.w1.weight": "model-00194-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.1.w2.weight": "model-00194-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.1.w3.weight": "model-00195-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.2.w1.weight": "model-00195-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.2.w2.weight": "model-00195-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.2.w3.weight": "model-00195-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.3.w1.weight": "model-00195-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.3.w2.weight": "model-00196-of-00201.safetensors", + "model.layers.77.block_sparse_moe.experts.3.w3.weight": "model-00196-of-00201.safetensors", + "model.layers.77.block_sparse_moe.gate.weight": "model-00194-of-00201.safetensors", + "model.layers.77.input_layernorm.weight": "model-00196-of-00201.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00196-of-00201.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00193-of-00201.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00194-of-00201.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00193-of-00201.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00194-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.0.w1.weight": "model-00196-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.0.w2.weight": "model-00196-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.0.w3.weight": "model-00197-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.1.w1.weight": "model-00197-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.1.w2.weight": "model-00197-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.1.w3.weight": "model-00197-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.2.w1.weight": "model-00197-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.2.w2.weight": "model-00198-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.2.w3.weight": "model-00198-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.3.w1.weight": "model-00198-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.3.w2.weight": "model-00198-of-00201.safetensors", + "model.layers.78.block_sparse_moe.experts.3.w3.weight": "model-00198-of-00201.safetensors", + "model.layers.78.block_sparse_moe.gate.weight": "model-00196-of-00201.safetensors", + "model.layers.78.input_layernorm.weight": "model-00198-of-00201.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00198-of-00201.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00196-of-00201.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00196-of-00201.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00196-of-00201.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00196-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.0.w1.weight": "model-00199-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.0.w2.weight": "model-00199-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.0.w3.weight": "model-00199-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.1.w1.weight": "model-00199-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.1.w2.weight": "model-00199-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.1.w3.weight": "model-00200-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.2.w1.weight": "model-00200-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.2.w2.weight": "model-00200-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.2.w3.weight": "model-00200-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.3.w1.weight": "model-00200-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.3.w2.weight": "model-00201-of-00201.safetensors", + "model.layers.79.block_sparse_moe.experts.3.w3.weight": "model-00201-of-00201.safetensors", + "model.layers.79.block_sparse_moe.gate.weight": "model-00199-of-00201.safetensors", + "model.layers.79.input_layernorm.weight": "model-00201-of-00201.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00201-of-00201.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00198-of-00201.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00199-of-00201.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00198-of-00201.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00199-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00201.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00201.safetensors", + "model.layers.8.block_sparse_moe.gate.weight": "model-00021-of-00201.safetensors", + "model.layers.8.input_layernorm.weight": "model-00023-of-00201.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00023-of-00201.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00021-of-00201.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00021-of-00201.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00021-of-00201.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00021-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00201.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00201.safetensors", + "model.layers.9.block_sparse_moe.gate.weight": "model-00024-of-00201.safetensors", + "model.layers.9.input_layernorm.weight": "model-00026-of-00201.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00026-of-00201.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00023-of-00201.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00024-of-00201.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00023-of-00201.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00024-of-00201.safetensors", + "model.norm.weight": "model-00201-of-00201.safetensors" + } +}