Upload folder using huggingface_hub

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "BeaverAI/Lazarus-2407-100B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 12288,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 96,
+  "num_hidden_layers": 72,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.1",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.1"
+}

model-00001-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1455bbe1d407f4be444e831e8c272f28fbb51e51d1ec694206e98ebeca62d14
+size 4932552432

model-00002-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77185491901e13318c4ccf9a0e16b4eadf558aa51d16cdc2b56db4f98319ceaf
+size 4831938528

model-00003-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd610259aecb6e9677e10bc702ab639ea2e82079ef520167d5f214d37d359e05
+size 4882269816

model-00004-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5281737cf0d787fd01efe4172e4160a40f4995b8317cb7f1893fbd2c2e3d97a
+size 4831889136

model-00005-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a14a55a3a5f45a319247d5769141cb5473730b483aff02602636604015fe6c6
+size 4831938520

model-00006-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d81c16d45fbf38c9dc67e626052e47b9566850bd66a8d5944f37b33eec0143
+size 4831938528

model-00007-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d830a51d866e04df3b8e6db7f0fb47fe2b489e79c526360f17f82ab5a6f37e3
+size 4882269832

model-00008-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1748ebf448fd0ab806e34fb47afc95c15376a3f5190a3f99c0e91a983a74aeb
+size 4831889152

model-00009-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3438d44f805411b282d76fa41f2b8a3089530090027edbd02acf021be107b309
+size 4831938536

model-00010-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc8e280fc555525774ebcbc05c0cd2be1f81b15fd37c7645087581b990d387a
+size 4831938544

model-00011-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6635400cee5e198f62f3a3b4237cffdec7d50fcd3719476dae2b9b6df2ca309
+size 4882269832

model-00012-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458d61903a616c46af2cc9e25ee6a618c663936c5d512590cbe3b7bf99d63c30
+size 4831889152

model-00013-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2c07ebb530d5f5bbd987dbca4dc8bccedd8e6d2d28b7beec1a923487b0a25d
+size 4831938536

model-00014-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62205e6023d7378c2071bc9c8edca3d11bd94469e0b9de9293604985754eaa81
+size 4831938544

model-00015-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90596ff335226ebe233520314bd2b0623b452c495fc429c134eed2d45b62c915
+size 4882269832

model-00016-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de80289bc45fc9faf054872ca6471beb33f1ba5366fd3af2b795c693710c32dc
+size 4831889152

model-00017-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f2399d970278cf880a7796a51a24510fb99dd59ef037ed929d715a4d9d8e78
+size 4831938536

model-00018-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d86b811e0aca57886872382fb48931bdcd87a1547d6973c2074427b604821d
+size 4831938544

model-00019-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5796ecc0a95440a100ced16b02e84f55688a351e443b06db484ea4cb5e2db07
+size 4882269832

model-00020-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851a114bffbf5fbba1f9398863c0f873e4691ecf72c408c91f423f7aa76494de
+size 4831889152

model-00021-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37b6f85209df9e4953341d282b1a7e7a987a278840b4b4715d0cfd269d754b5
+size 4831938536

model-00022-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2edc47dee5d5e2136188ce0a95083a6772d5a1ff39b306520e16b578d881f644
+size 4831938544

model-00023-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f424f1e1e773b0d2be2951b853fd353a336b0300fe02428e6c7f437456b281b2
+size 4882269832

model-00024-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1be3cee467084a6764491316b334d49ba9100efa65c5abc5272eb47257db1c1e
+size 4831889152

model-00025-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e481ed3d982211c5d46c47c15f32359f6576c18e98ac7424965bc020809929a9
+size 4831938536

model-00026-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6a167721d3aaa8b8ee3c0dc987e7c548679140ecc88df336537cdcd2e52bdf
+size 4831938544

model-00027-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b3702e0d9d55d4952e3e5538808b21c6e1fa343f762db7704bc508db3ef03b
+size 4882269832

model-00028-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d01acf9f5e8e7ba5450c2080de6f3c7aa68cf55197d8128cdd2eedf46b9489c
+size 4831889152

model-00029-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dbce054653bfaa57567a1c7590ce2d747fa0908af52a97e6542330d929a39b6
+size 4831938536

model-00030-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be581c2b01b86ff647e8a9d564c023f87ed8c50fdca6c5b16b4a36b3227187ba
+size 4831938544

model-00031-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e0ae2cd15720ad1b7578366c50bc931a9d718d1cf7045e1dbb5f99d036c1df
+size 4882269832

model-00032-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b07878f65f407b28ab547b9e6186d1f5b230daac0e5b03f574d20232201872b
+size 4831889152

model-00033-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9730f8f5618dd4f244cd56d44eb92e94fe34e4640cd17ae4837d55a0e4b4119e
+size 4831938536

model-00034-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777922c1a52e24e803141c60f0d9de556c5072e22beed870f94335b102f5404c
+size 4831938544

model-00035-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dbecdaba0390923923e8151fcde7fb00cdd7f61d7acabbcff4c4fc02e615557
+size 4882269832

model-00036-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca23e9d324f77d044784679a3f914beaedd76bba4fabf05aa45f7fa524f471d
+size 4831889152

model-00037-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86073bb13574c96b9e30579715482b19f48252ee074fb5e3f385e90aa0e89a8a
+size 4831938536

model-00038-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2593a8a062820516b551440da8a9d234c39a4f37eed3350257a8204a814498a3
+size 4831938544

model-00039-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee50312e3517b912d34b8478c2de8c6f3d77672ae54777ab492e62a1d7b0d26b
+size 4882269832

model-00040-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608c4f4e1c54b6aa685f67bb067113330a1aeac2ee563df9a12ca4e1ac08191a
+size 4831889152

model-00041-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db7b3783704794c056b1dc7a4870612bac2fce5215121b881177f3d6815c3a27
+size 4831938536

model-00042-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ecbe755cf4c30cd8fb1f2c7ffe8b899b4a52029b9e30a5a175df04d27b1baa0
+size 2214666928

model.safetensors.index.json

@@ -0,0 +1,658 @@
+{
+  "metadata": {
+    "total_size": 200927502336
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00042-of-00042.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00042.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00042.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00042.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00042.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00042.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00042.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00042.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00007-of-00042.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00042.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00007-of-00042.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00042.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00042.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00042.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00042.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00042.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00042.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00042.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00042.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00042.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00042.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00042.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00042.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00009-of-00042.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00042.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00042.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00009-of-00042.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00042.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00010-of-00042.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00042.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00042.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00010-of-00042.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00042.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00011-of-00042.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00011-of-00042.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00042.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00011-of-00042.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00042.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00042.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00011-of-00042.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00011-of-00042.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00042.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00011-of-00042.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00042.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00042.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00042.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00042.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00042.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00012-of-00042.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00042.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00042.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00042.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00013-of-00042.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00042.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00042.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00013-of-00042.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00042.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00014-of-00042.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00042.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00042.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00014-of-00042.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00042.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00015-of-00042.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00015-of-00042.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00042.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00015-of-00042.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00042.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00014-of-00042.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00015-of-00042.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00015-of-00042.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00042.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00015-of-00042.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00042.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00042.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00042.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00042.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00042.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00016-of-00042.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00042.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00017-of-00042.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00042.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00042.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00017-of-00042.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00017-of-00042.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00018-of-00042.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00042.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00042.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00042.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00042.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00042.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00042.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00042.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00042.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00018-of-00042.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00042.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00019-of-00042.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00019-of-00042.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00042.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00019-of-00042.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00042.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00042.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00019-of-00042.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00019-of-00042.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00042.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00019-of-00042.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00042.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00042.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00042.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00042.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00042.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00020-of-00042.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00042.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00021-of-00042.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00042.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00020-of-00042.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00021-of-00042.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00042.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00022-of-00042.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00042.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00021-of-00042.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00022-of-00042.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00022-of-00042.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00023-of-00042.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00023-of-00042.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00042.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00023-of-00042.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00042.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00022-of-00042.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00023-of-00042.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00023-of-00042.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00023-of-00042.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00023-of-00042.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00023-of-00042.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00023-of-00042.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00023-of-00042.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00023-of-00042.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00023-of-00042.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00042.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00042.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00042.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00042.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00042.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00042.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00042.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00042.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00042.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00024-of-00042.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00042.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00025-of-00042.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00025-of-00042.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00024-of-00042.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00025-of-00042.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00025-of-00042.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00026-of-00042.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00026-of-00042.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00025-of-00042.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00026-of-00042.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00026-of-00042.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00027-of-00042.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00027-of-00042.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00027-of-00042.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00027-of-00042.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00027-of-00042.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00026-of-00042.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00027-of-00042.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00027-of-00042.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00027-of-00042.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00027-of-00042.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00027-of-00042.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00027-of-00042.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00027-of-00042.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00027-of-00042.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00027-of-00042.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00028-of-00042.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00028-of-00042.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00029-of-00042.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00029-of-00042.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00028-of-00042.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00029-of-00042.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00029-of-00042.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00042.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00042.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00030-of-00042.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00030-of-00042.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00029-of-00042.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00030-of-00042.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00030-of-00042.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00031-of-00042.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00031-of-00042.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00031-of-00042.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00031-of-00042.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00031-of-00042.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00030-of-00042.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00031-of-00042.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00031-of-00042.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00031-of-00042.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00031-of-00042.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00031-of-00042.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00031-of-00042.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00031-of-00042.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00031-of-00042.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00031-of-00042.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00032-of-00042.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00032-of-00042.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00033-of-00042.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00033-of-00042.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00032-of-00042.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00033-of-00042.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00033-of-00042.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00034-of-00042.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00042.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00033-of-00042.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00034-of-00042.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00034-of-00042.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00035-of-00042.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00035-of-00042.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00035-of-00042.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00035-of-00042.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00035-of-00042.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00034-of-00042.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00042.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00042.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00042.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00035-of-00042.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00035-of-00042.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00035-of-00042.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00035-of-00042.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00035-of-00042.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00035-of-00042.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00035-of-00042.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00035-of-00042.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00035-of-00042.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00036-of-00042.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00036-of-00042.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00037-of-00042.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00037-of-00042.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00036-of-00042.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00037-of-00042.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00037-of-00042.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00038-of-00042.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00038-of-00042.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00037-of-00042.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00038-of-00042.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00038-of-00042.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00039-of-00042.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00039-of-00042.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00039-of-00042.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00039-of-00042.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00039-of-00042.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00038-of-00042.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00039-of-00042.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00039-of-00042.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00039-of-00042.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00039-of-00042.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00039-of-00042.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00039-of-00042.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00039-of-00042.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00039-of-00042.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00039-of-00042.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00040-of-00042.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00040-of-00042.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00041-of-00042.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00041-of-00042.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00040-of-00042.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00042.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00042.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00041-of-00042.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00041-of-00042.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00042-of-00042.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00042-of-00042.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00042-of-00042.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00042-of-00042.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00041-of-00042.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00042.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00042.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00042.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00042.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00042.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00042.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00042.safetensors",
+    "model.norm.weight": "model-00042-of-00042.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583