diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e9285b77e31fa599c9bc90e9497f94db17ce2ef6 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "MixtralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 6144, + "initializer_range": 0.02, + "intermediate_size": 16384, + "max_position_embeddings": 65536, + "model_type": "mixtral", + "num_attention_heads": 48, + "num_experts_per_tok": 2, + "num_hidden_layers": 56, + "num_key_value_heads": 8, + "num_local_experts": 8, + "output_router_logits": false, + "rms_norm_eps": 1e-05, + "rope_theta": 1000000, + "router_aux_loss_coef": 0.001, + "router_jitter_noise": 0.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.40.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..05283793bb9bb2f7a016ed90b7bedee58adbea84 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.40.0.dev0" +} diff --git a/model-00001-of-00059.safetensors b/model-00001-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2135f23ff915254d167838e39f6b25076e036105 --- /dev/null +++ b/model-00001-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b039c0a113de62272bace9f5c48c70503ad3290bb0c65abbdb9ace27ca565cfd +size 4998663696 diff --git a/model-00002-of-00059.safetensors b/model-00002-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c392466f19de1da11528498a22ddcec6d0677f1b --- /dev/null +++ b/model-00002-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83771f7731be5a4e216fbd8efe7c4c4733a556c3c72124cea3f5f7963a95eed +size 4806799120 diff --git a/model-00003-of-00059.safetensors b/model-00003-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b7e6d2216f2efaff979328e2a8b79d9cb407cb5 --- /dev/null +++ b/model-00003-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7bd17848981fb13c16c1a850a5ae1492af74c79088fe1e60bbd9591aff42354 +size 4806799120 diff --git a/model-00004-of-00059.safetensors b/model-00004-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ec22aba2b8953a6282dde59a99b7d9a1342f792 --- /dev/null +++ b/model-00004-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51783101334dfaa9d62e05c47adc95f1695754e1b3cdecc5a324db51f0ac4fd4 +size 4806799120 diff --git a/model-00005-of-00059.safetensors b/model-00005-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90be51f3b56a35590f4d476332346185e741a344 --- /dev/null +++ b/model-00005-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:884dda6f0757f11ea3366cbc5b1d961cbffa65c826f95295a296b481b2b69e75 +size 4806799120 diff --git a/model-00006-of-00059.safetensors b/model-00006-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c41c5321fbc88d8c06026ec50ab9dafbf8139614 --- /dev/null +++ b/model-00006-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc1bd6bfcf7e0c91488f0c07f8a8e50b3596e8cd7ed862ce8d4e6292ed34935 +size 4806799120 diff --git a/model-00007-of-00059.safetensors b/model-00007-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb5b26176c494a79892a189323bf1b8d835f4108 --- /dev/null +++ b/model-00007-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e463627c8cfcacb6d6be922384f4484c4085df0fe6e3da8b8bcad631ee6c650 +size 4806799120 diff --git a/model-00008-of-00059.safetensors b/model-00008-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cbe3cca57c1c28959a084e3a9c5c67a57e9ae643 --- /dev/null +++ b/model-00008-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1147ec45481fa3ef9a917d08a78865ef42ecb7c4c538a4edc498609ec678b221 +size 4806799120 diff --git a/model-00009-of-00059.safetensors b/model-00009-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08a101c3ce13aa0bf35108300fca1442048c2378 --- /dev/null +++ b/model-00009-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf912f23bad0f9692c58c76c93d361876d6a61e6b6372b40eae51422ecb5457 +size 4806799120 diff --git a/model-00010-of-00059.safetensors b/model-00010-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b19efb604ce19d9427c133f8c912427bd645fbb1 --- /dev/null +++ b/model-00010-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b635201338d2a2911a035f05023c94e60c14920e731be6652b9b89c6b05cf938 +size 4806799120 diff --git a/model-00011-of-00059.safetensors b/model-00011-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de72ded706e8e048ea763385c4cdeb605da72b6c --- /dev/null +++ b/model-00011-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee35393493b397e5d6c556b938b6c836c945a430ccadd1947c03a0f67921023 +size 4806799136 diff --git a/model-00012-of-00059.safetensors b/model-00012-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..41330f9d26a178714da9ad378dece1c7695d2497 --- /dev/null +++ b/model-00012-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94f67175581edbcd500caa4cb4edc1f362d020e85fc022c4f0e3e6f9ab69ce2d +size 4806799152 diff --git a/model-00013-of-00059.safetensors b/model-00013-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..29c167b50ca063b0d797acfe086249c50ef620ee --- /dev/null +++ b/model-00013-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ae57ed917b0d0ed903839e9dc22bdb0f0590ebb9e867a98b5b4f9aff1d3515 +size 4806799152 diff --git a/model-00014-of-00059.safetensors b/model-00014-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2be28fcf3fdab51dced2f5248af92cc825b6e476 --- /dev/null +++ b/model-00014-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5d5156330ec725b6c89877fea2eef67038846d0afec96dab2bc2531e604ac4 +size 4806799152 diff --git a/model-00015-of-00059.safetensors b/model-00015-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01e51e90619ba30872c962791143734153941dc8 --- /dev/null +++ b/model-00015-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ac8d1c058daaed35d2add3b9e4b17173b43d2a125a3da5fa45e1658e8878fd +size 4806799152 diff --git a/model-00016-of-00059.safetensors b/model-00016-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f96dcfdc1d223bbfd7cc3ca39d914b52a13ff3a --- /dev/null +++ b/model-00016-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a478c73e34122bf98ca7dcbdc5acd3e7c6f8d8aa60529c272e832875d5216f +size 4806799152 diff --git a/model-00017-of-00059.safetensors b/model-00017-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f74b9b5713a02718696d22ea0746fc0896450ac --- /dev/null +++ b/model-00017-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca496a9d0cc2a323b9cb8ff5a8ce05aacee3795c0698acaabc13e5ad052a77d +size 4806799152 diff --git a/model-00018-of-00059.safetensors b/model-00018-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9006d8e7af843f304ea7cd745fd1c9be8ae23fb9 --- /dev/null +++ b/model-00018-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b4d36cd8cd6d5004fe197d2971c2d735ae95d0a7fca3d5b9764ba5ff9dc777c +size 4806799152 diff --git a/model-00019-of-00059.safetensors b/model-00019-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..77fec792afcc59c83c46db93e4fe57af869d9944 --- /dev/null +++ b/model-00019-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f21e8856c1bf685b87bdac2c54d0c4e7247757a98c6d5b43880759a9c14c8b1 +size 4806799152 diff --git a/model-00020-of-00059.safetensors b/model-00020-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb4b0b75e92907bb3a34d678243b624e881c3a14 --- /dev/null +++ b/model-00020-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:933dda96b69cdef0440e7e77b96d0286e8a00a2fc45234e3f5096a7150ef02a9 +size 4806799152 diff --git a/model-00021-of-00059.safetensors b/model-00021-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee38bd835363202c370c1d5e5ced90d94a646242 --- /dev/null +++ b/model-00021-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:616211f8ed279b2c133e9863bfb01c6bf061397dc879fa06676ab1c7a1bfeb0a +size 4806799152 diff --git a/model-00022-of-00059.safetensors b/model-00022-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e040e6cb7d3db24d9b40dda7f9eaf2a442a1c48c --- /dev/null +++ b/model-00022-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a127eae5266dd1fe645a45b425482d5c8052c5374f6e386e614a6733c6226bb +size 4806799152 diff --git a/model-00023-of-00059.safetensors b/model-00023-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6218529f92b174270fc933921797a2c17a68d825 --- /dev/null +++ b/model-00023-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4f29da3532e4937b99d1a5ece5457a97c846276c8ec4ef514281f90f4a9506e +size 4806799152 diff --git a/model-00024-of-00059.safetensors b/model-00024-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa09a75f80a1c6c530b5c3498eae48b3c3793f95 --- /dev/null +++ b/model-00024-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:063e0bbb5f2d783f2ce20cfaa014b234c81b370afe49587399386d99b50e3aae +size 4932529864 diff --git a/model-00025-of-00059.safetensors b/model-00025-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4aff8e862cbd33d95c4592deccee7c7f31701848 --- /dev/null +++ b/model-00025-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:040b7d741425ae5676099d9431dbbb55929159d33a8afd5feaf4b5c50f9d2800 +size 4995542848 diff --git a/model-00026-of-00059.safetensors b/model-00026-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3366f47fd8bd1055ae6c79ec42c5bd90d481213c --- /dev/null +++ b/model-00026-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06a45ea1f0841e8f214683fdabf89cec183f7e844849bf633b898bab8aa740e6 +size 4995542848 diff --git a/model-00027-of-00059.safetensors b/model-00027-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7a8bbde7c22fd74e924c965a543e7358ab75cde --- /dev/null +++ b/model-00027-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c6f5e468564e403a7cb3a97b84f778451ab92937e684b75122f90950df27849 +size 4932628288 diff --git a/model-00028-of-00059.safetensors b/model-00028-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5162b303ce242198fa96a3297f25703caff4fc08 --- /dev/null +++ b/model-00028-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b9a5ce26370f37727dc78305dc8dcfea7f3b102e9a894e2a8a5f3dde2f7ab89 +size 4806774344 diff --git a/model-00029-of-00059.safetensors b/model-00029-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c26e50657d9a5e89321bf08f732b31c0ffcf5cb2 --- /dev/null +++ b/model-00029-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0458c20683be80e6c814f17b233f7e3b651f461fa616079fa22542b2abff59f +size 4806799144 diff --git a/model-00030-of-00059.safetensors b/model-00030-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0cfaa74739b3acd7713ff22430f5c3e1b6756826 --- /dev/null +++ b/model-00030-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:790b0203791f80500dd1d3d15796ff4c72ab3cf78ea00dd96e51872d1722f585 +size 4806799144 diff --git a/model-00031-of-00059.safetensors b/model-00031-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7630b35b9f768a8868c96f54de779697624441b0 --- /dev/null +++ b/model-00031-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed11f4e9fe8b3f582ccf57245dba278c0b996042228a4c0ccd080f31bfd334d +size 4806799144 diff --git a/model-00032-of-00059.safetensors b/model-00032-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d62cf742dd84c53feb69c81e8e97e13126b4c6bd --- /dev/null +++ b/model-00032-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70e6bc0591fc8bec66d8756d2ffd04b59b4fd57ae93cdd441a76429884f1c83 +size 4806799144 diff --git a/model-00033-of-00059.safetensors b/model-00033-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fbd91089dbda7825f7d8e4cc3b46593282f492ce --- /dev/null +++ b/model-00033-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc00641c7de6181c059c414230046263b20ffce2807037a79ec467dcca8d201 +size 4806799152 diff --git a/model-00034-of-00059.safetensors b/model-00034-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5185df9862bdc631b0eaf0eb1edba6dd01529b2 --- /dev/null +++ b/model-00034-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7fcaa9f411b23bd1f5d0e6d25a7fab18aa420f64a2e4160550cb92c7f8bff6 +size 4806799152 diff --git a/model-00035-of-00059.safetensors b/model-00035-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da7a5aa876f9359d594de547a8cdaf9e83302abe --- /dev/null +++ b/model-00035-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65513f09da03f27cac48b3d87dbfb1e98929a31630deb9ab954405e735d3775 +size 4806799152 diff --git a/model-00036-of-00059.safetensors b/model-00036-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0824c82525cb78c3ebaa7234bbd761b35d9f18e5 --- /dev/null +++ b/model-00036-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c7f0a00e9d1d32899c8f9a85c2bab3f03b061a1d3f25466de8cf7cb6ee2dba +size 4806799152 diff --git a/model-00037-of-00059.safetensors b/model-00037-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..051c3bd7e6d005f81404f0a12e64f7d4356032b0 --- /dev/null +++ b/model-00037-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9414dcc7522d4cc765458ce6697aeb5286aa03de6d1204f42a470ff2f81a59ec +size 4806799152 diff --git a/model-00038-of-00059.safetensors b/model-00038-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7f0e7943f86e497fd03657dcb6ff6dfb337eebb --- /dev/null +++ b/model-00038-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f40497204a3f340f8894bda0df9bc65873c97f68cf91e68c9d42370bd4a457d +size 4806799152 diff --git a/model-00039-of-00059.safetensors b/model-00039-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..83d4155a48c5159f5afad0813d6a3a888112ce10 --- /dev/null +++ b/model-00039-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5adf314c52d78bf6ddc2778eb5bafceefcd25069cf6710f75c6770633a438a0c +size 4806799152 diff --git a/model-00040-of-00059.safetensors b/model-00040-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..034b541b9e5fc6cb7c2f172b1ec88b00578e9e38 --- /dev/null +++ b/model-00040-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3916f7db00d69d8aecb6d2597ca3b488a2829d3bd4d21fa4ed21dde311f0df8 +size 4806799152 diff --git a/model-00041-of-00059.safetensors b/model-00041-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ecf348397e12f9268105c2e9f3556ece82a09175 --- /dev/null +++ b/model-00041-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4556f1b7c3599f3a904dfe1e61dd22e655d29ed1eae614118078e216662c8650 +size 4806799152 diff --git a/model-00042-of-00059.safetensors b/model-00042-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1570cf47e931c474ab104326b9be1c50a7b990a2 --- /dev/null +++ b/model-00042-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef1fcc735bbf26a61623185ac500161757d4854a3b8b05c9826bba4a6633859e +size 4806799152 diff --git a/model-00043-of-00059.safetensors b/model-00043-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86b7df4fa1b827aa6b17185d3b87217c5520e397 --- /dev/null +++ b/model-00043-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d51d71c5598283092b9eebd69169d6002d08fabb92eb1de2e11d2f504c83f6d4 +size 4806799152 diff --git a/model-00044-of-00059.safetensors b/model-00044-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e65b9be5245f76a76c54aa39cf71ebf0bee03077 --- /dev/null +++ b/model-00044-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d280cf85760838c2108fa750401d271c5a5fa112c3a79dfaef1f61e81bf42e +size 4806799152 diff --git a/model-00045-of-00059.safetensors b/model-00045-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef38edd476c9b1646392db4ec0638935cfb9ce81 --- /dev/null +++ b/model-00045-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d291e6ad3383c50c6897a67a88050da4aa8fd78eca3fbbe46e65d9ff0e818cce +size 4806799152 diff --git a/model-00046-of-00059.safetensors b/model-00046-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91a510662a33689b390daa8ace47f6ebef8ddb8a --- /dev/null +++ b/model-00046-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa610e393ffb4182a6e6dda2115d54d297fb7ad721d96920644bc0942b753e8e +size 4806799152 diff --git a/model-00047-of-00059.safetensors b/model-00047-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3afd66f669aa18ea29f7529dd836e58cae7d65d9 --- /dev/null +++ b/model-00047-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b0069d8246eb8933fbd678fec8db10485c25ce399dce0bc8931a943657da3d3 +size 4806799152 diff --git a/model-00048-of-00059.safetensors b/model-00048-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f637b35cf200c98ef9e136d7913ab1cd1cb9a000 --- /dev/null +++ b/model-00048-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31204ed829f496213dfe6a02bcfcab65ed9f663f7b4b22e8535c60cfc929924f +size 4806799152 diff --git a/model-00049-of-00059.safetensors b/model-00049-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a50efae7921bc578b7a2f27b89e6473596fc62e1 --- /dev/null +++ b/model-00049-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23802ab6525c3872ed0c2a7ebc847040fe149d9f72e1dced2023dfa2eeff7364 +size 4806799152 diff --git a/model-00050-of-00059.safetensors b/model-00050-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f4c6f4681db8bd384c88cd518b088e7baa45688f --- /dev/null +++ b/model-00050-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9f848414b6bcf560542984d19cc94faa7308b067e8ec69048738dece7fff55 +size 4806799152 diff --git a/model-00051-of-00059.safetensors b/model-00051-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af9c8d692095670c226a30ebd802f9fcf307c500 --- /dev/null +++ b/model-00051-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d9ca778a8fa0990452e6a7a608a843006dcb6c2593b06b8016ef283a17b4850 +size 4806799152 diff --git a/model-00052-of-00059.safetensors b/model-00052-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef7ddd1426ad72c46ea8567b7ee4f8de9bbbd852 --- /dev/null +++ b/model-00052-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aeb24b7f8ae5411fec26a75183f40f8c05e6c43644a34dbddf355f94ed7e92a +size 4932529864 diff --git a/model-00053-of-00059.safetensors b/model-00053-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f196259b639e8307e83bf943a2877ea5b2ff8d30 --- /dev/null +++ b/model-00053-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4fb287833eda0711e626a9a9765d643a9747977c55c65bad3d11f96a57224ea +size 4995542848 diff --git a/model-00054-of-00059.safetensors b/model-00054-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..02a9bc803e86c05411b827b3b18266c2150921cd --- /dev/null +++ b/model-00054-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8bca1fa5fbb41e504e0088d00e046c560b40559caae963674238a5e5a10a855 +size 4995542848 diff --git a/model-00055-of-00059.safetensors b/model-00055-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..758aa93277a667b02adf213eaf774470f7b8fa11 --- /dev/null +++ b/model-00055-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494c0fdbe7d38f3c3b6df9b0b337b6d16146fa4f310da05ea26b8d29eb1fa00d +size 4932628288 diff --git a/model-00056-of-00059.safetensors b/model-00056-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d91a1724f20f7ccfb4f65c1c9c780c28b12e6b6 --- /dev/null +++ b/model-00056-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2680bf3a5f2803881f1164882eb47f20f82d6ffd35a25b23482838bb0b10d58d +size 4806774344 diff --git a/model-00057-of-00059.safetensors b/model-00057-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..158c6fc5779b9361284aa3b148d8060268193353 --- /dev/null +++ b/model-00057-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0335abaca20c4b89229bb3aac1d851fc3c4424e3fa870da8f090598fc995b724 +size 4806799144 diff --git a/model-00058-of-00059.safetensors b/model-00058-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4313640f0f0d33031d37977d6f21d9ee126ffe35 --- /dev/null +++ b/model-00058-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77d0c8251542040e7892afc7640b70863f42702a3d50b0cfb2abc9b1076f3ba6 +size 4806799144 diff --git a/model-00059-of-00059.safetensors b/model-00059-of-00059.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a76552e9dd0caf78f75cc898a270708203c6602c --- /dev/null +++ b/model-00059-of-00059.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3062eb4fe54e1c505e5aaa729d723d0f200f0c5ff5e14a553ab784a2caf3ecc +size 997233472 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..805c18819ee3c4a51164b634df4f4033c74583ad --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1746 @@ +{ + "metadata": { + "total_size": 281241268224 + }, + "weight_map": { + "lm_head.weight": "model-00059-of-00059.safetensors", + "model.embed_tokens.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00059.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00059.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00059.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00059.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00059.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00059.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.1.block_sparse_moe.gate.weight": "model-00002-of-00059.safetensors", + "model.layers.1.input_layernorm.weight": "model-00003-of-00059.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00059.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00059.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00059.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00059.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.10.block_sparse_moe.gate.weight": "model-00011-of-00059.safetensors", + "model.layers.10.input_layernorm.weight": "model-00012-of-00059.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00059.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00059.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00059.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00059.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.11.block_sparse_moe.gate.weight": "model-00012-of-00059.safetensors", + "model.layers.11.input_layernorm.weight": "model-00013-of-00059.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00059.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00059.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00059.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00059.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00059.safetensors", + "model.layers.12.input_layernorm.weight": "model-00014-of-00059.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00059.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00059.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00059.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00059.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.13.block_sparse_moe.gate.weight": "model-00014-of-00059.safetensors", + "model.layers.13.input_layernorm.weight": "model-00015-of-00059.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00059.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00059.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00059.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00059.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.14.block_sparse_moe.gate.weight": "model-00015-of-00059.safetensors", + "model.layers.14.input_layernorm.weight": "model-00016-of-00059.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00059.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00059.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00059.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00059.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.15.block_sparse_moe.gate.weight": "model-00016-of-00059.safetensors", + "model.layers.15.input_layernorm.weight": "model-00017-of-00059.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00059.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00059.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00059.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00059.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.16.block_sparse_moe.gate.weight": "model-00017-of-00059.safetensors", + "model.layers.16.input_layernorm.weight": "model-00018-of-00059.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00059.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00059.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00059.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00059.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.17.block_sparse_moe.gate.weight": "model-00018-of-00059.safetensors", + "model.layers.17.input_layernorm.weight": "model-00019-of-00059.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00059.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00059.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00059.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00059.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.18.block_sparse_moe.gate.weight": "model-00019-of-00059.safetensors", + "model.layers.18.input_layernorm.weight": "model-00020-of-00059.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00059.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00059.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00059.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00059.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00021-of-00059.safetensors", + "model.layers.19.block_sparse_moe.gate.weight": "model-00020-of-00059.safetensors", + "model.layers.19.input_layernorm.weight": "model-00021-of-00059.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00059.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00059.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00059.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00059.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00059.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00059.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00059.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00059.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00059.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00059.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00022-of-00059.safetensors", + "model.layers.20.block_sparse_moe.gate.weight": "model-00021-of-00059.safetensors", + "model.layers.20.input_layernorm.weight": "model-00022-of-00059.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00059.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00059.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00059.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00059.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00023-of-00059.safetensors", + "model.layers.21.block_sparse_moe.gate.weight": "model-00022-of-00059.safetensors", + "model.layers.21.input_layernorm.weight": "model-00023-of-00059.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00023-of-00059.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00059.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00059.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00059.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00024-of-00059.safetensors", + "model.layers.22.block_sparse_moe.gate.weight": "model-00023-of-00059.safetensors", + "model.layers.22.input_layernorm.weight": "model-00024-of-00059.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00024-of-00059.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00059.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00059.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00059.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00025-of-00059.safetensors", + "model.layers.23.block_sparse_moe.gate.weight": "model-00025-of-00059.safetensors", + "model.layers.23.input_layernorm.weight": "model-00025-of-00059.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00025-of-00059.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00059.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00025-of-00059.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00059.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00026-of-00059.safetensors", + "model.layers.24.block_sparse_moe.gate.weight": "model-00026-of-00059.safetensors", + "model.layers.24.input_layernorm.weight": "model-00026-of-00059.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00026-of-00059.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00059.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00026-of-00059.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00059.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00026-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00027-of-00059.safetensors", + "model.layers.25.block_sparse_moe.gate.weight": "model-00027-of-00059.safetensors", + "model.layers.25.input_layernorm.weight": "model-00027-of-00059.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00027-of-00059.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00027-of-00059.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00027-of-00059.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00059.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00027-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00028-of-00059.safetensors", + "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.26.block_sparse_moe.gate.weight": "model-00028-of-00059.safetensors", + "model.layers.26.input_layernorm.weight": "model-00029-of-00059.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00029-of-00059.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00028-of-00059.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00028-of-00059.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00028-of-00059.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00028-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.27.block_sparse_moe.gate.weight": "model-00029-of-00059.safetensors", + "model.layers.27.input_layernorm.weight": "model-00030-of-00059.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00030-of-00059.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00029-of-00059.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00029-of-00059.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00029-of-00059.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00029-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00030-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.28.block_sparse_moe.gate.weight": "model-00030-of-00059.safetensors", + "model.layers.28.input_layernorm.weight": "model-00031-of-00059.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00031-of-00059.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00030-of-00059.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00030-of-00059.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00030-of-00059.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00030-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00031-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.29.block_sparse_moe.gate.weight": "model-00031-of-00059.safetensors", + "model.layers.29.input_layernorm.weight": "model-00032-of-00059.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00032-of-00059.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00031-of-00059.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00031-of-00059.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00031-of-00059.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00031-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00059.safetensors", + "model.layers.3.input_layernorm.weight": "model-00005-of-00059.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00059.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00059.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00059.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00059.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00032-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.30.block_sparse_moe.gate.weight": "model-00032-of-00059.safetensors", + "model.layers.30.input_layernorm.weight": "model-00033-of-00059.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00033-of-00059.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00032-of-00059.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00032-of-00059.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00032-of-00059.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00032-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00033-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.31.block_sparse_moe.gate.weight": "model-00033-of-00059.safetensors", + "model.layers.31.input_layernorm.weight": "model-00034-of-00059.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00034-of-00059.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00033-of-00059.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00033-of-00059.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00033-of-00059.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00033-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.4.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.4.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.4.w3.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.6.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.6.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.6.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.7.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.7.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.experts.7.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.32.block_sparse_moe.gate.weight": "model-00034-of-00059.safetensors", + "model.layers.32.input_layernorm.weight": "model-00035-of-00059.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00035-of-00059.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00034-of-00059.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00034-of-00059.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00034-of-00059.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00034-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.4.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.5.w1.weight": "model-00035-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.5.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.5.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.6.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.6.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.6.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.7.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.7.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.experts.7.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.33.block_sparse_moe.gate.weight": "model-00035-of-00059.safetensors", + "model.layers.33.input_layernorm.weight": "model-00036-of-00059.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00036-of-00059.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00035-of-00059.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00035-of-00059.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00035-of-00059.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00035-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.4.w1.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.4.w2.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.4.w3.weight": "model-00036-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.5.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.6.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.6.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.6.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.7.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.7.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.experts.7.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.34.block_sparse_moe.gate.weight": "model-00036-of-00059.safetensors", + "model.layers.34.input_layernorm.weight": "model-00037-of-00059.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00037-of-00059.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00036-of-00059.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00036-of-00059.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00036-of-00059.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00036-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.4.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.5.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.5.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.5.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.6.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.6.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.6.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.7.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.7.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.experts.7.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.35.block_sparse_moe.gate.weight": "model-00037-of-00059.safetensors", + "model.layers.35.input_layernorm.weight": "model-00038-of-00059.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00038-of-00059.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00037-of-00059.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00037-of-00059.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00037-of-00059.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00037-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.4.w1.weight": "model-00038-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.4.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.4.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.5.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.5.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.5.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.6.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.6.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.6.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.7.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.7.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.experts.7.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.36.block_sparse_moe.gate.weight": "model-00038-of-00059.safetensors", + "model.layers.36.input_layernorm.weight": "model-00039-of-00059.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00039-of-00059.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00038-of-00059.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00038-of-00059.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00038-of-00059.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00038-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00039-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.4.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.4.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.4.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.5.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.5.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.5.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.6.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.6.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.6.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.7.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.7.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.experts.7.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.37.block_sparse_moe.gate.weight": "model-00039-of-00059.safetensors", + "model.layers.37.input_layernorm.weight": "model-00040-of-00059.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00040-of-00059.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00039-of-00059.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00039-of-00059.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00039-of-00059.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00039-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00040-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.4.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.4.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.4.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.5.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.5.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.5.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.6.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.6.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.6.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.7.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.7.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.experts.7.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.38.block_sparse_moe.gate.weight": "model-00040-of-00059.safetensors", + "model.layers.38.input_layernorm.weight": "model-00041-of-00059.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00041-of-00059.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00040-of-00059.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00040-of-00059.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00040-of-00059.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00040-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00041-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.4.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.4.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.4.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.5.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.5.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.5.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.6.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.6.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.6.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.7.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.7.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.experts.7.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.39.block_sparse_moe.gate.weight": "model-00041-of-00059.safetensors", + "model.layers.39.input_layernorm.weight": "model-00042-of-00059.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00042-of-00059.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00041-of-00059.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00041-of-00059.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00041-of-00059.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00041-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.4.block_sparse_moe.gate.weight": "model-00005-of-00059.safetensors", + "model.layers.4.input_layernorm.weight": "model-00006-of-00059.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00059.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00059.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00059.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00059.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.2.w1.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.2.w2.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.2.w3.weight": "model-00042-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.3.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.3.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.3.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.4.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.4.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.4.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.5.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.5.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.5.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.6.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.6.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.6.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.7.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.7.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.experts.7.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.40.block_sparse_moe.gate.weight": "model-00042-of-00059.safetensors", + "model.layers.40.input_layernorm.weight": "model-00043-of-00059.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00043-of-00059.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00042-of-00059.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00042-of-00059.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00042-of-00059.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00042-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.2.w1.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.2.w2.weight": "model-00043-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.2.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.3.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.3.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.3.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.4.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.4.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.4.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.5.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.5.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.5.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.6.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.6.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.6.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.7.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.7.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.experts.7.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.41.block_sparse_moe.gate.weight": "model-00043-of-00059.safetensors", + "model.layers.41.input_layernorm.weight": "model-00044-of-00059.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00044-of-00059.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00043-of-00059.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00043-of-00059.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00043-of-00059.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00043-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.2.w1.weight": "model-00044-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.2.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.2.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.3.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.3.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.3.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.4.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.4.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.4.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.5.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.5.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.5.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.6.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.6.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.6.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.7.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.7.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.experts.7.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.42.block_sparse_moe.gate.weight": "model-00044-of-00059.safetensors", + "model.layers.42.input_layernorm.weight": "model-00045-of-00059.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00045-of-00059.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00044-of-00059.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00044-of-00059.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00044-of-00059.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00044-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00045-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.2.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.2.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.2.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.3.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.3.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.3.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.4.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.4.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.4.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.5.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.5.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.5.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.6.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.6.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.6.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.7.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.7.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.experts.7.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.43.block_sparse_moe.gate.weight": "model-00045-of-00059.safetensors", + "model.layers.43.input_layernorm.weight": "model-00046-of-00059.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00046-of-00059.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00045-of-00059.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00045-of-00059.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00045-of-00059.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00045-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00046-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00046-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00046-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.2.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.2.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.2.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.3.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.3.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.3.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.4.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.4.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.4.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.5.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.5.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.5.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.6.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.6.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.6.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.7.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.7.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.experts.7.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.44.block_sparse_moe.gate.weight": "model-00046-of-00059.safetensors", + "model.layers.44.input_layernorm.weight": "model-00047-of-00059.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00047-of-00059.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00046-of-00059.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00046-of-00059.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00046-of-00059.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00046-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00047-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00047-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00047-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.2.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.2.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.2.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.3.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.3.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.3.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.4.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.4.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.4.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.5.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.5.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.5.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.6.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.6.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.6.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.7.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.7.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.experts.7.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.45.block_sparse_moe.gate.weight": "model-00047-of-00059.safetensors", + "model.layers.45.input_layernorm.weight": "model-00048-of-00059.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00048-of-00059.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00047-of-00059.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00047-of-00059.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00047-of-00059.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00047-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00048-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00048-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00048-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.2.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.2.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.2.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.3.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.3.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.3.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.4.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.4.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.4.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.5.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.5.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.5.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.6.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.6.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.6.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.7.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.7.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.experts.7.w3.weight": "model-00049-of-00059.safetensors", + "model.layers.46.block_sparse_moe.gate.weight": "model-00048-of-00059.safetensors", + "model.layers.46.input_layernorm.weight": "model-00049-of-00059.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00049-of-00059.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00048-of-00059.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00048-of-00059.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00048-of-00059.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00048-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00049-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00049-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.2.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.2.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.2.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.3.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.3.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.3.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.4.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.4.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.4.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.5.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.5.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.5.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.6.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.6.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.6.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.7.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.7.w2.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.experts.7.w3.weight": "model-00050-of-00059.safetensors", + "model.layers.47.block_sparse_moe.gate.weight": "model-00049-of-00059.safetensors", + "model.layers.47.input_layernorm.weight": "model-00050-of-00059.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00050-of-00059.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00049-of-00059.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00049-of-00059.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00049-of-00059.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00049-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00050-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.2.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.2.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.2.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.3.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.3.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.3.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.4.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.4.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.4.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.5.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.5.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.5.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.6.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.6.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.6.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.7.w1.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.7.w2.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.experts.7.w3.weight": "model-00051-of-00059.safetensors", + "model.layers.48.block_sparse_moe.gate.weight": "model-00050-of-00059.safetensors", + "model.layers.48.input_layernorm.weight": "model-00051-of-00059.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00051-of-00059.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00050-of-00059.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00050-of-00059.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00050-of-00059.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00050-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.2.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.2.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.2.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.3.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.3.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.3.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.4.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.4.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.4.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.5.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.5.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.5.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.6.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.6.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.6.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.7.w1.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.7.w2.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.experts.7.w3.weight": "model-00052-of-00059.safetensors", + "model.layers.49.block_sparse_moe.gate.weight": "model-00051-of-00059.safetensors", + "model.layers.49.input_layernorm.weight": "model-00052-of-00059.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00052-of-00059.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00051-of-00059.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00051-of-00059.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00051-of-00059.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00051-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00059.safetensors", + "model.layers.5.input_layernorm.weight": "model-00007-of-00059.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00059.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00059.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00059.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00059.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.2.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.2.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.2.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.3.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.3.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.3.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.4.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.4.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.4.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.5.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.5.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.5.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.6.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.6.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.6.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.7.w1.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.7.w2.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.experts.7.w3.weight": "model-00053-of-00059.safetensors", + "model.layers.50.block_sparse_moe.gate.weight": "model-00053-of-00059.safetensors", + "model.layers.50.input_layernorm.weight": "model-00053-of-00059.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00053-of-00059.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00052-of-00059.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00053-of-00059.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00052-of-00059.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00052-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.2.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.2.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.2.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.3.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.3.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.3.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.4.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.4.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.4.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.5.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.5.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.5.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.6.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.6.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.6.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.7.w1.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.7.w2.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.experts.7.w3.weight": "model-00054-of-00059.safetensors", + "model.layers.51.block_sparse_moe.gate.weight": "model-00054-of-00059.safetensors", + "model.layers.51.input_layernorm.weight": "model-00054-of-00059.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00054-of-00059.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00053-of-00059.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00054-of-00059.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00053-of-00059.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00054-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.2.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.2.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.2.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.3.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.3.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.3.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.4.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.4.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.4.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.5.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.5.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.5.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.6.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.6.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.6.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.7.w1.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.7.w2.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.experts.7.w3.weight": "model-00055-of-00059.safetensors", + "model.layers.52.block_sparse_moe.gate.weight": "model-00055-of-00059.safetensors", + "model.layers.52.input_layernorm.weight": "model-00055-of-00059.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00055-of-00059.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00055-of-00059.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00055-of-00059.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00054-of-00059.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00055-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.2.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.2.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.2.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.3.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.3.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.3.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.4.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.4.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.4.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.5.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.5.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.5.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.6.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.6.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.6.w3.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.7.w1.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.7.w2.weight": "model-00056-of-00059.safetensors", + "model.layers.53.block_sparse_moe.experts.7.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.53.block_sparse_moe.gate.weight": "model-00056-of-00059.safetensors", + "model.layers.53.input_layernorm.weight": "model-00057-of-00059.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00057-of-00059.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00056-of-00059.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00056-of-00059.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00056-of-00059.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00056-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.2.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.2.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.2.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.3.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.3.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.3.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.4.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.4.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.4.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.5.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.5.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.5.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.6.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.6.w2.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.6.w3.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.7.w1.weight": "model-00057-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.7.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.54.block_sparse_moe.experts.7.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.54.block_sparse_moe.gate.weight": "model-00057-of-00059.safetensors", + "model.layers.54.input_layernorm.weight": "model-00058-of-00059.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00058-of-00059.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00057-of-00059.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00057-of-00059.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00057-of-00059.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00057-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.2.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.2.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.2.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.3.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.3.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.3.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.4.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.4.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.4.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.5.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.5.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.5.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.6.w1.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.6.w2.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.6.w3.weight": "model-00058-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.7.w1.weight": "model-00059-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.7.w2.weight": "model-00059-of-00059.safetensors", + "model.layers.55.block_sparse_moe.experts.7.w3.weight": "model-00059-of-00059.safetensors", + "model.layers.55.block_sparse_moe.gate.weight": "model-00058-of-00059.safetensors", + "model.layers.55.input_layernorm.weight": "model-00059-of-00059.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00059-of-00059.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00058-of-00059.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00058-of-00059.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00058-of-00059.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00058-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.6.block_sparse_moe.gate.weight": "model-00007-of-00059.safetensors", + "model.layers.6.input_layernorm.weight": "model-00008-of-00059.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00059.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00059.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00059.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00059.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00059.safetensors", + "model.layers.7.input_layernorm.weight": "model-00009-of-00059.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00059.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00059.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00059.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00059.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.8.block_sparse_moe.gate.weight": "model-00009-of-00059.safetensors", + "model.layers.8.input_layernorm.weight": "model-00010-of-00059.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00059.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00059.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00059.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00059.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00059.safetensors", + "model.layers.9.block_sparse_moe.gate.weight": "model-00010-of-00059.safetensors", + "model.layers.9.input_layernorm.weight": "model-00011-of-00059.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00059.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00059.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00059.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00059.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00059.safetensors", + "model.norm.weight": "model-00059-of-00059.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..a52c50a199269393cd1548c7e6a77a654bd2001b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,5 @@ +{ + "bos_token": "", + "eos_token": "", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..81730cd96b4768bd1a77a4bd8269c72ea708870b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}