Upload 45 files

README.md

@@ -1,3 +1,41 @@
 ---
-license: apache-2.0
+base_model:
+- Sao10K/Fimbulvetr-11B-v2
+- Undi95/Mistral-11B-CC-Air-RP
+library_name: transformers
+tags:
+- mergekit
+- merge
+
 ---
+# merge
+
+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:
+* [Sao10K/Fimbulvetr-11B-v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2)
+* [Undi95/Mistral-11B-CC-Air-RP](https://huggingface.co/Undi95/Mistral-11B-CC-Air-RP)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: Sao10K/Fimbulvetr-11B-v2
+      layer_range: [0, 40]
+  - sources:
+    - model: Undi95/Mistral-11B-CC-Air-RP
+      layer_range: [8, 48]
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Sao10K/Fimbulvetr-11B-v2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+slices:
+  - sources:
+    - model: Sao10K/Fimbulvetr-11B-v2
+      layer_range: [0, 40]
+  - sources:
+    - model: Undi95/Mistral-11B-CC-Air-RP
+      layer_range: [8, 48]
+merge_method: passthrough
+dtype: bfloat16

model-00001-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6137adc53b263e9e25ce1f3525bad88474276b7bb0ec4ca94bbec557cf614b87
+size 960521552

model-00002-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b06b4443c5c168dcd1013509da9f815e1fcb21dc2ecd6b805d3930478b4f3b6
+size 905995864

model-00003-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009ddbb675e4f51e0befdd97bad247e547c745492745895e2541911522148213
+size 989890728

model-00004-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:051ded11d8a7c6ab36d50a3a358a1123aaebe61e03cabbd0663c02b2e7e00a72
+size 998296072

model-00005-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54e248705b4bfb857a1073e3870cb33407daed83129d273955010400089e945
+size 981502456

model-00006-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9446d97dd5f0cdbbfaf1e6c43209f3c79fb8cf11fd217b622c75c540155eaca3
+size 922798696

model-00007-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4581c73af7566384a005bde2070c0bf617b3a2597fa84ef6914cc38eac261aab
+size 989890728

model-00008-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57a50485c4b113f384ab25982c5bd0233e0636f2b8dbc042773e9da1c6a263e
+size 989890728

model-00009-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bfa1e946e6efedf9c7e7dcccec1832c533c3baae6db343ea7c789919c233afc
+size 989890728

model-00010-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b956e635066b0f5e9c60f3535accbb214e1fc573f6d318b4d50754247fa1f5d
+size 989890728

model-00011-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:122f6d04775c13f16a8ec1197987e377f85404c2d817c3ec134f63402a700993
+size 956353248

model-00012-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f7820884916329648d63a5ffdc507ef6ff54ac334301a99f7fe7590b16e83c
+size 989890728

model-00013-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055c44bd135872426121be9133aa3b3cf764927a0cb6bad0e07f2d35e8e2412f
+size 989890728

model-00014-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48cd9524f6b8a039ada6523578f60751db0633d1544bc27b871118b9ca954035
+size 989890728

model-00015-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17f5a7cf1fed8f57bc84fbc73589c410260b2cf83b328b8d7c91b2caa32069d7
+size 989890728

model-00016-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d61d29aa0d615e5a4242377c712e24d8fd26484cb8cbea34e17cc3f278cd450
+size 998296072

model-00017-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16b852805efcdab8296413714ca932e67403087bd65a60ea4c5d37d96b4f76c
+size 981502456

model-00018-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0972143120c809adf6c80a0f03d8fe72016c38291a9ed1734083d93b78fb6213
+size 922798696

model-00019-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031ac15376d86e429851c76abdbfd5b5fa865be10259154dbb6770cb2a806681
+size 989890728

model-00020-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ca7dea6447a37e2aaa0536b3f0e7d5d83afdb858c329e26493c2453a9bab61
+size 989882424

model-00021-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20774fe3f54a47deb047a0428aa6067ceaedea31a2e012844a72315fd8b288ee
+size 989899032

model-00022-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2a53d79deecb0ed605182d061aae56d0e87d556d4d5b98e4d2d04500234f28
+size 956353240

model-00023-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2364a8ab1cbb866ebb02ac78e0f157110e5ce8a68e1a0be32a3595ad344c24
+size 989890728

model-00024-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608a5261f5dcf7858c9e2fb67bc214dad21d0003f5440f6a2940c8b0929665b9
+size 989890728

model-00025-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19eea0ccd4943ebe4aad29b2d3110f77877edf7303ff880f07852beaada29b4
+size 989890728

model-00026-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc621e9f1186ab53e1de54ed19e6b3b9817994f612fc458ac9ec9541cc3cad11
+size 989890728

model-00027-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f863523754d367b8df1501d6b02398cb2f46e9c43bf78d9cd2927055eae6b4fa
+size 989890728

model-00028-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ccd21fa029065273a68de14aa3006c846634e64ff1fa5b9e738f123ed0bbe6
+size 998296072

model-00029-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca7f80722a7b96bef8e2e9c7fbd72dce6b4a93fd442540849e3692cb79860834
+size 981502456

model-00030-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dbc5cfeb436bbc2c6fa1f7c4c559955aeeef0ed889af8f6d69f080e85733523
+size 922790384

model-00031-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:070ad600bec8ad780e9c045002e969016eec9dbcfea1fcc6f4a0d2189b5d3664
+size 989890728

model-00032-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2430603e5a13e27d04ba84130d63c9b25f09f1c49f8d4a82510547dffb837a
+size 989890728

model-00033-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8426ffc0a26e7d15921b25174708b3a2ab2f7f4bf69fb35fffdfb8131d0f25a4
+size 998287760

model-00034-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584212d848efa531de74af121ba720a75a399d37b1b903282aa4e0add9c986aa
+size 947956192

model-00035-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e44aacf4e6c91c47d9dec1554c5a31d826e888cef921542542062bf005a719
+size 905995856

model-00036-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deeb1efd14bc344d258e0c98e287d8a6c9db5203d229b65e2b3b23e59ee1d21b
+size 989890720

model-00037-of-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12404373abf67c29a0906369d08cc14514920286f6454ba01d98d76b2b30126
+size 285238624

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 35422216192}, "weight_map": {"lm_head.weight": "model-00001-of-00037.safetensors", "model.embed_tokens.weight": "model-00001-of-00037.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00037.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00037.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00037.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00037.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00037.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00037.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00037.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00037.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00037.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00037.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00037.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00037.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00037.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00037.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00037.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00037.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00037.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00037.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00037.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00037.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00037.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00037.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00037.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00037.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00003-of-00037.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00037.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00037.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00037.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00037.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00037.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00037.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00037.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00037.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00037.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00037.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00037.safetensors", "model.layers.43.input_layernorm.weight": "model-00003-of-00037.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00037.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00003-of-00037.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00037.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00037.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00037.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00003-of-00037.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00037.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00037.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00037.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00037.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00037.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00037.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00037.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00037.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00037.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00037.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00037.safetensors", "model.layers.44.input_layernorm.weight": "model-00004-of-00037.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00037.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00004-of-00037.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00037.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00037.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00037.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00004-of-00037.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00037.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00037.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00037.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00037.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00037.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00037.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00037.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00037.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00037.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00037.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00037.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00037.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00037.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00005-of-00037.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00037.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00037.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00037.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00005-of-00037.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00037.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00037.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00037.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00037.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00037.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00037.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00037.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00037.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00037.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00037.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00037.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00037.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00037.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00037.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00037.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00037.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00037.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00037.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00037.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00037.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00037.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00037.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00037.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00037.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00037.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00037.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00037.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00037.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00037.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00037.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00037.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00037.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00037.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00037.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00037.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00037.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00037.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00037.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00037.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00037.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00037.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00037.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00037.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00037.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00037.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00037.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00037.safetensors", "model.layers.48.input_layernorm.weight": "model-00007-of-00037.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00037.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00007-of-00037.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00037.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00037.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00037.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00037.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00037.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00037.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00037.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00037.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00037.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00037.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00037.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00037.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00037.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00037.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00037.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00037.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00037.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00037.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00037.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00037.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00037.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00037.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00037.safetensors", "model.layers.50.input_layernorm.weight": "model-00009-of-00037.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00037.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00009-of-00037.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00037.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00037.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00037.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00037.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00037.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00037.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00037.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00037.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00037.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00037.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00037.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00037.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00037.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00010-of-00037.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00037.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00037.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00037.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00011-of-00037.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00037.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00037.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00037.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00037.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00037.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00037.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00037.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00037.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00037.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00037.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00037.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00037.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00037.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00037.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00011-of-00037.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00037.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00037.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00037.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00037.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00037.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00037.safetensors", "model.layers.20.input_layernorm.weight": "model-00011-of-00037.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00011-of-00037.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00037.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00037.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00037.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00037.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00037.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00037.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00037.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00037.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00037.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00037.safetensors", "model.layers.53.input_layernorm.weight": "model-00012-of-00037.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00037.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00012-of-00037.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00037.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00037.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00013-of-00037.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00037.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00037.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00037.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00037.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00037.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00013-of-00037.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00037.safetensors", "model.layers.54.input_layernorm.weight": "model-00013-of-00037.safetensors", "model.layers.22.input_layernorm.weight": "model-00013-of-00037.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00013-of-00037.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00037.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00037.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00037.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00037.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00014-of-00037.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00037.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00037.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00037.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00037.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00014-of-00037.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00037.safetensors", "model.layers.55.input_layernorm.weight": "model-00014-of-00037.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00037.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00014-of-00037.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00037.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00014-of-00037.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00037.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00015-of-00037.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00037.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00015-of-00037.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00037.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00015-of-00037.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00037.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00015-of-00037.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00037.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00015-of-00037.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00037.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00015-of-00037.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00037.safetensors", "model.layers.56.input_layernorm.weight": "model-00015-of-00037.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00037.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00015-of-00037.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00037.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00015-of-00037.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00037.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00015-of-00037.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00037.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00016-of-00037.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00037.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00016-of-00037.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00037.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00016-of-00037.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00037.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00016-of-00037.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00037.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00016-of-00037.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00037.safetensors", "model.layers.57.input_layernorm.weight": "model-00016-of-00037.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00037.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00016-of-00037.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00037.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00016-of-00037.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00037.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00016-of-00037.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00016-of-00037.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00016-of-00037.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00037.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00016-of-00037.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00037.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00017-of-00037.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00037.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00017-of-00037.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00037.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00017-of-00037.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00037.safetensors", "model.layers.58.input_layernorm.weight": "model-00017-of-00037.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00037.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00017-of-00037.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00017-of-00037.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00017-of-00037.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00017-of-00037.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00037.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00037.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00037.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00017-of-00037.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00037.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00018-of-00037.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00037.safetensors", "model.layers.59.input_layernorm.weight": "model-00018-of-00037.safetensors", "model.layers.27.input_layernorm.weight": "model-00018-of-00037.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00018-of-00037.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00037.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00018-of-00037.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00018-of-00037.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00037.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00037.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00037.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00037.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00018-of-00037.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00037.safetensors", "model.layers.60.input_layernorm.weight": "model-00018-of-00037.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00037.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00019-of-00037.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00037.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00019-of-00037.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00019-of-00037.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00037.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00037.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00037.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00037.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00019-of-00037.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00037.safetensors", "model.layers.61.input_layernorm.weight": "model-00019-of-00037.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00037.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00019-of-00037.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00020-of-00037.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00020-of-00037.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00020-of-00037.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00020-of-00037.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00020-of-00037.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00020-of-00037.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00037.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00020-of-00037.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00037.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00020-of-00037.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00037.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00020-of-00037.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00037.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00020-of-00037.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00037.safetensors", "model.layers.3.input_layernorm.weight": "model-00020-of-00037.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00020-of-00037.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00020-of-00037.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00021-of-00037.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00021-of-00037.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00021-of-00037.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00021-of-00037.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00021-of-00037.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00021-of-00037.safetensors", "model.layers.62.input_layernorm.weight": "model-00021-of-00037.safetensors", "model.layers.30.input_layernorm.weight": "model-00021-of-00037.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00021-of-00037.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00021-of-00037.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00021-of-00037.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00037.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00021-of-00037.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00021-of-00037.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00021-of-00037.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00021-of-00037.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00021-of-00037.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00021-of-00037.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00021-of-00037.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00037.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00022-of-00037.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00037.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00022-of-00037.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00037.safetensors", "model.layers.63.input_layernorm.weight": "model-00022-of-00037.safetensors", "model.layers.31.input_layernorm.weight": "model-00022-of-00037.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00022-of-00037.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00022-of-00037.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00022-of-00037.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00037.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00022-of-00037.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00022-of-00037.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00022-of-00037.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00037.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00022-of-00037.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00037.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00022-of-00037.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00037.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00022-of-00037.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00037.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00022-of-00037.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00037.safetensors", "model.layers.64.input_layernorm.weight": "model-00022-of-00037.safetensors", "model.layers.32.input_layernorm.weight": "model-00022-of-00037.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00023-of-00037.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00023-of-00037.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00023-of-00037.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00023-of-00037.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00023-of-00037.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00023-of-00037.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00023-of-00037.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00037.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00037.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00037.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00023-of-00037.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00037.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00037.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00023-of-00037.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00023-of-00037.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00037.safetensors", "model.layers.65.input_layernorm.weight": "model-00023-of-00037.safetensors", "model.layers.33.input_layernorm.weight": "model-00023-of-00037.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00023-of-00037.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00024-of-00037.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00024-of-00037.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00024-of-00037.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00037.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00024-of-00037.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00024-of-00037.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00024-of-00037.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00024-of-00037.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00037.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00024-of-00037.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00037.safetensors", "model.layers.34.input_layernorm.weight": "model-00024-of-00037.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00037.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00024-of-00037.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00025-of-00037.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00025-of-00037.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00037.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00025-of-00037.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00025-of-00037.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00025-of-00037.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00025-of-00037.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00037.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00025-of-00037.safetensors", "model.layers.67.input_layernorm.weight": "model-00025-of-00037.safetensors", "model.layers.35.input_layernorm.weight": "model-00025-of-00037.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00025-of-00037.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00025-of-00037.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00037.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00026-of-00037.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00026-of-00037.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00026-of-00037.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00026-of-00037.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00026-of-00037.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00026-of-00037.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00026-of-00037.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00026-of-00037.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00026-of-00037.safetensors", "model.layers.68.input_layernorm.weight": "model-00026-of-00037.safetensors", "model.layers.36.input_layernorm.weight": "model-00026-of-00037.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00026-of-00037.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00026-of-00037.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00026-of-00037.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00026-of-00037.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00027-of-00037.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00027-of-00037.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00027-of-00037.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00027-of-00037.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00027-of-00037.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00027-of-00037.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00027-of-00037.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00027-of-00037.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00027-of-00037.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00027-of-00037.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00027-of-00037.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00027-of-00037.safetensors", "model.layers.69.input_layernorm.weight": "model-00027-of-00037.safetensors", "model.layers.37.input_layernorm.weight": "model-00027-of-00037.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00027-of-00037.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00027-of-00037.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00027-of-00037.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00027-of-00037.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00027-of-00037.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00028-of-00037.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00028-of-00037.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00028-of-00037.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00028-of-00037.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00028-of-00037.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00028-of-00037.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00028-of-00037.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00028-of-00037.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00028-of-00037.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00028-of-00037.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00028-of-00037.safetensors", "model.layers.70.input_layernorm.weight": "model-00028-of-00037.safetensors", "model.layers.38.input_layernorm.weight": "model-00028-of-00037.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00028-of-00037.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00028-of-00037.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00028-of-00037.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00028-of-00037.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00028-of-00037.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00028-of-00037.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00028-of-00037.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00028-of-00037.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00028-of-00037.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00029-of-00037.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00029-of-00037.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00029-of-00037.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00029-of-00037.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00029-of-00037.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00029-of-00037.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00029-of-00037.safetensors", "model.layers.71.input_layernorm.weight": "model-00029-of-00037.safetensors", "model.layers.39.input_layernorm.weight": "model-00029-of-00037.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00029-of-00037.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00029-of-00037.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00029-of-00037.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00029-of-00037.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00029-of-00037.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00029-of-00037.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00029-of-00037.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00029-of-00037.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00029-of-00037.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00029-of-00037.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00029-of-00037.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00029-of-00037.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00029-of-00037.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00030-of-00037.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00030-of-00037.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00030-of-00037.safetensors", "model.layers.4.input_layernorm.weight": "model-00030-of-00037.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00030-of-00037.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00030-of-00037.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00030-of-00037.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00030-of-00037.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00030-of-00037.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00030-of-00037.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00030-of-00037.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00030-of-00037.safetensors", "model.layers.72.input_layernorm.weight": "model-00030-of-00037.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00030-of-00037.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00030-of-00037.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00030-of-00037.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00030-of-00037.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00030-of-00037.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00030-of-00037.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00030-of-00037.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00030-of-00037.safetensors", "model.layers.73.input_layernorm.weight": "model-00030-of-00037.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00031-of-00037.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00031-of-00037.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00031-of-00037.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00031-of-00037.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00031-of-00037.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00031-of-00037.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00031-of-00037.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00031-of-00037.safetensors", "model.layers.74.input_layernorm.weight": "model-00031-of-00037.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00031-of-00037.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00031-of-00037.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00031-of-00037.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00031-of-00037.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00031-of-00037.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00031-of-00037.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00031-of-00037.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00031-of-00037.safetensors", "model.layers.75.input_layernorm.weight": "model-00031-of-00037.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00031-of-00037.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00032-of-00037.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00032-of-00037.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00032-of-00037.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00032-of-00037.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00032-of-00037.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00032-of-00037.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00032-of-00037.safetensors", "model.layers.76.input_layernorm.weight": "model-00032-of-00037.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00032-of-00037.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00032-of-00037.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00032-of-00037.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00032-of-00037.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00032-of-00037.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00032-of-00037.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00032-of-00037.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00032-of-00037.safetensors", "model.layers.77.input_layernorm.weight": "model-00032-of-00037.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00032-of-00037.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00032-of-00037.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00033-of-00037.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00033-of-00037.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00033-of-00037.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00033-of-00037.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00033-of-00037.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00033-of-00037.safetensors", "model.layers.78.input_layernorm.weight": "model-00033-of-00037.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00033-of-00037.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00033-of-00037.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00033-of-00037.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00033-of-00037.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00033-of-00037.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00033-of-00037.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00033-of-00037.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00033-of-00037.safetensors", "model.layers.79.input_layernorm.weight": "model-00033-of-00037.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00033-of-00037.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00033-of-00037.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00033-of-00037.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00033-of-00037.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00033-of-00037.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00034-of-00037.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00034-of-00037.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00034-of-00037.safetensors", "model.layers.5.input_layernorm.weight": "model-00034-of-00037.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00034-of-00037.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00034-of-00037.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00034-of-00037.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00034-of-00037.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00034-of-00037.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00034-of-00037.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00034-of-00037.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.input_layernorm.weight": "model-00034-of-00037.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00034-of-00037.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00034-of-00037.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00034-of-00037.safetensors", "model.layers.7.input_layernorm.weight": "model-00034-of-00037.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00035-of-00037.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00035-of-00037.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00035-of-00037.safetensors", "model.layers.40.input_layernorm.weight": "model-00035-of-00037.safetensors", "model.layers.8.input_layernorm.weight": "model-00035-of-00037.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00035-of-00037.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00035-of-00037.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00035-of-00037.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00035-of-00037.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00036-of-00037.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00036-of-00037.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00036-of-00037.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00036-of-00037.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00036-of-00037.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00036-of-00037.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00036-of-00037.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00036-of-00037.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00036-of-00037.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00036-of-00037.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00036-of-00037.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00036-of-00037.safetensors", "model.layers.41.input_layernorm.weight": "model-00036-of-00037.safetensors", "model.layers.9.input_layernorm.weight": "model-00036-of-00037.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00036-of-00037.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00036-of-00037.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00036-of-00037.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00036-of-00037.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00036-of-00037.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00037-of-00037.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00037-of-00037.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00037-of-00037.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00037-of-00037.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00037-of-00037.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00037-of-00037.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00037-of-00037.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00037-of-00037.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00037-of-00037.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00037-of-00037.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00037-of-00037.safetensors", "model.norm.weight": "model-00037-of-00037.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}