Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# 100b
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* ./largestral
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: ./largestral
+        layer_range: [0, 54]
+  - sources:
+      - model: ./largestral
+        layer_range: [70,88]
+merge_method: passthrough
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "./largestral",
+  "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": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 32768
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+slices:
+  - sources:
+      - model: ./largestral
+        layer_range: [0, 54]
+  - sources:
+      - model: ./largestral
+        layer_range: [70,88]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd03ff284e4324bd3a31511d1bbaab644cc30dff53db64c37acbcac7f91769c
+size 4378928504

model-00002-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b95ba9950ba6d154a2d4d8379a7b0a487770b4d1b0809f1fd76f554a58fec90
+size 4907411088

model-00003-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f723328d474667d0128c4dae515e96bc354978ec5e5e0a131e0e2144a7205cdd
+size 4806747904

model-00004-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df0b636a686027a11922d0a5265982869dd1a6d99dd216e926e719e778046d0
+size 4831938544

model-00005-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26079a878ffb3be350f2f3be6dcc2b3c8b94a809fbc1055878d6bb16ea5e38cd
+size 4831938552

model-00006-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ac509de863f43d57058123802c886b765d1de504a5704a71150016d470b6c1
+size 4907411096

model-00007-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1445451312364a818b8d00f22e0983d4a4a708f7e64d1651f43f2770c8ad281
+size 4806747904

model-00008-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6f38d4d0512e7e044d86216d455cefaf4024183ef0cc8268ab2ed07c69ec2c
+size 4831938536

model-00009-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7084ebd6036043235dd8a4a4f61e85f00919fa343cd44abc4f2ded7ed1937bf6
+size 4831938552

model-00010-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37402d9de86f9774b1f6e8c94ba931a33af1e9d34a0d4d9e65d6ce7badabf06f
+size 4907411096

model-00011-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a292a527dd49a1191477ca9878ec626be03acd8ffcdc961ef416d461588b5532
+size 4806747904

model-00012-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f78ca4dfbf798d916ece12866a4a692fa8be0808bd4e5baba864d375273a536
+size 4831938544

model-00013-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617a866352025f1056601bf416c9011318f19bcd8395131f5258f239b978f881
+size 4831938552

model-00014-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3b45ee06ddb1fcf6efe798413b2be4387dd18355c7470b9010d0626a027e66
+size 4907411088

model-00015-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee053dfe5e767594eaaa306257c81413091b81a9d16f65f148bdeff214fd3f8
+size 4806747904

model-00016-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01feebcd156a59cd271ceb70db8c2e278b04d40931520842822a5f039b3d4e0
+size 4831938544

model-00017-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59bcbf4ff95cbc81bb37c89bbaff63dc9a38aa8d9bb6129f6322a77e86b094af
+size 4831938552

model-00018-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:147aa39b3c962b8c3b1b73f2128e36940d99c01e763afc3d757f7fa0b8fc6315
+size 4907411096

model-00019-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb07a3afb493bf99c13a6fa57faebacb441eb9f0360e499cb68f42a8b389a92c
+size 4806747904

model-00020-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:470c827d90faaba2494a66097a188b4301a96a69a18a4ef0ecfdb6d9c264fa5d
+size 4831938544

model-00021-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7743d28ff7a220e9bfaea6391933f54f7df74b5fd1af228f8706fd6c010a2f
+size 4831938544

model-00022-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f89b01006b9ec7d89e4ff8c3e7b3d28dbdba56c1aeb920d6896dbfabe867ff
+size 4907411096

model-00023-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ccb7a480ffb48d1b98944c6b8e8acf3a639b6a900970c66127e9f683505c455
+size 4806747904

model-00024-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ba6f2e8e813e11b61a8e23eb509acb01c9fc58865afff33ce51f2f21e7a298
+size 4831938544

model-00025-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e44a26af05c606e72af0bd8ec64e805de1af850a047cd4d5e449870ec31df4
+size 4831938552

model-00026-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357a8c44ed120b7818e232833ee03c5ed2246d7d15c26eaa3689b205255cdf59
+size 4907411096

model-00027-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7fb3e1e017c583ffb055694d47d4667ebbb83e504fe9eef236d2e07778f0225
+size 4806747896

model-00028-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d1d588d58e6df0372b37731f2af1d99018690dad65250f0eadb0ce990e3647
+size 4831938544

model-00029-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f266d30470d820efca4001cab2f79291f0368347c200eb68e8750fb5bad93b5f
+size 4831938552

model-00030-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6b7a53e4350c55fb11cb82ffacd7f988c363040f23235da3b1b6e6b7c93c6e
+size 4907411080

model-00031-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120a01b8ba2a250f158ce543fcc00d79ebe6e967c2b196b8067f9156e3065b60
+size 4806747896

model-00032-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a951a4eb571e45279ce61fe2d385a7ab27d83ffe2ae5c42bd3bf81fd5939c926
+size 4831938544

model-00033-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf96bfe477ada0c1eb8e0e520a759ce9444ff8f7fc52d4da3eb7ab25b2339b39
+size 4831938552

model-00034-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac09d38c846528d0595b568da4fd00e6326487df01097ad1e2f6340a58f86894
+size 4907411096

model-00035-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09bc65f20cf5625454cf36d4bc840cbbf126e7d55576d1da3132b5fb8f4b8ae
+size 4806747904

model-00036-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a96da07c5f47875d37214173db9cdf6039239b35d4f7e27ef4a7b15e1713720
+size 4831938544

model-00037-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f473e9d44ba0602bcf99f2e6f8aeed3704bed162e179e0cc7fc5c07be94b53cd
+size 4831938536

model-00038-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97df327fe66e618ede014bfa59571e74538c8e952e0c9fdf53e95f3b6ef2a869
+size 4907411096

model-00039-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d4be47ed0d718953e227f65b358383f8faff8e927487c36c1cf646308d4c7a
+size 4806747904

model-00040-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f5950fa2eb49fd8ca3af4b28e2b86d783242377cb782e493dcd7dff75b58a7
+size 4831938544

model-00041-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10058b8f5aad558fa467b156c2133a8404d3738ee5362041269f99f61831a0b5
+size 4831938552

model-00042-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ef423990873bd8cc3dfd6bd56d5ae1a689bf6af9351bf9253d7a450f747e8a
+size 2768290856

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 200927502336}, "weight_map": {"lm_head.weight": "model-00001-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-00001-of-00042.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00042.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-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-00002-of-00042.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00042.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00042.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00042.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00042.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00042.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00042.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00042.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00042.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00042.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00042.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00042.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00042.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00042.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00042.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00042.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00042.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00042.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00042.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00042.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00042.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00042.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00042.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00042.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00042.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00042.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00042.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00042.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00042.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00042.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00042.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00042.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00042.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00042.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00042.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00042.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00042.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00042.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00042.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00042.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00042.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00042.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00042.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00042.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00042.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00042.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00042.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00042.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00042.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00042.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00042.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00042.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00042.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00042.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00042.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00042.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00042.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00042.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00042.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00042.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00042.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00042.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00042.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00042.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00042.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00042.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00042.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00042.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00042.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00042.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00042.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00042.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00042.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00042.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00042.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00042.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00042.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00042.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00042.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00042.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00042.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00042.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00042.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00042.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.input_layernorm.weight": "model-00011-of-00042.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00042.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00042.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00042.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00042.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00042.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00012-of-00042.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00042.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00042.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00042.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00042.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00042.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00042.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00042.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00042.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00012-of-00042.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00042.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00013-of-00042.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00042.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00042.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00042.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00042.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.input_layernorm.weight": "model-00013-of-00042.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00042.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00042.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00042.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00042.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00042.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00042.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00014-of-00042.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00014-of-00042.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00042.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00042.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00042.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00015-of-00042.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00015-of-00042.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.input_layernorm.weight": "model-00015-of-00042.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00042.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00042.safetensors", "model.layers.31.input_layernorm.weight": "model-00015-of-00042.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00015-of-00042.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00042.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00016-of-00042.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00042.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00042.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00042.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00042.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.input_layernorm.weight": "model-00016-of-00042.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00016-of-00042.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00016-of-00042.safetensors", "model.layers.33.input_layernorm.weight": "model-00016-of-00042.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00016-of-00042.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00017-of-00042.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00017-of-00042.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00017-of-00042.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00017-of-00042.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00017-of-00042.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00017-of-00042.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.input_layernorm.weight": "model-00017-of-00042.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00017-of-00042.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00017-of-00042.safetensors", "model.layers.35.input_layernorm.weight": "model-00017-of-00042.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00042.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00018-of-00042.safetensors", "model.layers.36.input_layernorm.weight": "model-00018-of-00042.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00018-of-00042.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00042.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00018-of-00042.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00042.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00018-of-00042.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00042.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00042.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.input_layernorm.weight": "model-00019-of-00042.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00019-of-00042.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00042.safetensors", "model.layers.38.input_layernorm.weight": "model-00019-of-00042.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00019-of-00042.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00019-of-00042.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00020-of-00042.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00042.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00042.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00042.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00042.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.input_layernorm.weight": "model-00020-of-00042.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00042.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00042.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00042.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00020-of-00042.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00042.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00042.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00042.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00042.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00042.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00042.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.input_layernorm.weight": "model-00021-of-00042.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00042.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00021-of-00042.safetensors", "model.layers.41.input_layernorm.weight": "model-00021-of-00042.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00042.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00022-of-00042.safetensors", "model.layers.42.input_layernorm.weight": "model-00022-of-00042.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00022-of-00042.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00042.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00022-of-00042.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00022-of-00042.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00022-of-00042.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00023-of-00042.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00023-of-00042.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.input_layernorm.weight": "model-00023-of-00042.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00023-of-00042.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00023-of-00042.safetensors", "model.layers.44.input_layernorm.weight": "model-00023-of-00042.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00023-of-00042.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00023-of-00042.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00024-of-00042.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00024-of-00042.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00024-of-00042.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00024-of-00042.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00024-of-00042.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.input_layernorm.weight": "model-00024-of-00042.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00024-of-00042.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00024-of-00042.safetensors", "model.layers.46.input_layernorm.weight": "model-00024-of-00042.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00024-of-00042.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00025-of-00042.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00025-of-00042.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00025-of-00042.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00025-of-00042.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00025-of-00042.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00025-of-00042.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.input_layernorm.weight": "model-00025-of-00042.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00025-of-00042.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00025-of-00042.safetensors", "model.layers.48.input_layernorm.weight": "model-00025-of-00042.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00026-of-00042.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00026-of-00042.safetensors", "model.layers.49.input_layernorm.weight": "model-00026-of-00042.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00026-of-00042.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00026-of-00042.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00026-of-00042.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00026-of-00042.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00026-of-00042.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00027-of-00042.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00027-of-00042.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.input_layernorm.weight": "model-00027-of-00042.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00027-of-00042.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00027-of-00042.safetensors", "model.layers.50.input_layernorm.weight": "model-00027-of-00042.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00027-of-00042.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00027-of-00042.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00028-of-00042.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00028-of-00042.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00028-of-00042.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00028-of-00042.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00028-of-00042.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.input_layernorm.weight": "model-00028-of-00042.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00028-of-00042.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00028-of-00042.safetensors", "model.layers.52.input_layernorm.weight": "model-00028-of-00042.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00028-of-00042.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00029-of-00042.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00029-of-00042.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00029-of-00042.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00029-of-00042.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00029-of-00042.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00029-of-00042.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.input_layernorm.weight": "model-00029-of-00042.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00029-of-00042.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00029-of-00042.safetensors", "model.layers.6.input_layernorm.weight": "model-00029-of-00042.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00030-of-00042.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00030-of-00042.safetensors", "model.layers.7.input_layernorm.weight": "model-00030-of-00042.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00030-of-00042.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00030-of-00042.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00030-of-00042.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00030-of-00042.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00030-of-00042.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00031-of-00042.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00031-of-00042.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.input_layernorm.weight": "model-00031-of-00042.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00031-of-00042.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00031-of-00042.safetensors", "model.layers.55.input_layernorm.weight": "model-00031-of-00042.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00031-of-00042.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00031-of-00042.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00032-of-00042.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00032-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-00032-of-00042.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00032-of-00042.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00032-of-00042.safetensors", "model.layers.57.input_layernorm.weight": "model-00032-of-00042.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00032-of-00042.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00033-of-00042.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00033-of-00042.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00033-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-00033-of-00042.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00033-of-00042.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00033-of-00042.safetensors", "model.layers.59.input_layernorm.weight": "model-00033-of-00042.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00034-of-00042.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00034-of-00042.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00034-of-00042.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00034-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.60.input_layernorm.weight": "model-00034-of-00042.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00034-of-00042.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00034-of-00042.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00034-of-00042.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00034-of-00042.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00034-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-00035-of-00042.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00035-of-00042.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00035-of-00042.safetensors", "model.layers.62.input_layernorm.weight": "model-00035-of-00042.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00035-of-00042.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00035-of-00042.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00036-of-00042.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00036-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-00036-of-00042.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00036-of-00042.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00036-of-00042.safetensors", "model.layers.8.input_layernorm.weight": "model-00036-of-00042.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00036-of-00042.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00037-of-00042.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00037-of-00042.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00037-of-00042.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00037-of-00042.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00037-of-00042.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00037-of-00042.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.input_layernorm.weight": "model-00037-of-00042.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00037-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-00037-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-00038-of-00042.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00038-of-00042.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00038-of-00042.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00038-of-00042.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00038-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-00039-of-00042.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00039-of-00042.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00039-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-00039-of-00042.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00039-of-00042.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00039-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-00040-of-00042.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00040-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-00040-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.70.input_layernorm.weight": "model-00040-of-00042.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00040-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-00041-of-00042.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00041-of-00042.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00041-of-00042.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00041-of-00042.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00041-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.9.input_layernorm.weight": "model-00041-of-00042.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00042-of-00042.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00042-of-00042.safetensors", "model.norm.weight": "model-00042-of-00042.safetensors"}}

tokenizer.model

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