Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+---
+# FINGU-AI/L3-78b-Large-v1
+
+## Overview
+`FINGU-AI/L3-78b-Large-v1` is a powerful causal language model designed for a variety of natural language processing (NLP) tasks, including machine translation, text generation, and chat-based applications. This model is particularly useful for translating between languages, as well as supporting other custom NLP tasks through flexible input.
+
+## Example Usage
+
+### Installation
+Make sure to install the required packages:
+
+```bash
+pip install torch transformers
+```
+### Loading the Model
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Model and Tokenizer
+model_id = 'FINGU-AI/L3-78b-Large-v1'
+model = AutoModelForCausalLM.from_pretrained(model_id, attn_implementation="sdpa", torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model.to('cuda')
+
+# Input Messages for Translation
+messages = [
+    {"role": "system", "content": "translate korean to Uzbek"},
+    {"role": "user", "content": """새로운 은행 계좌를 개설하는 절차는 다음과 같습니다:
+
+1. 계좌 개설 목적과 신분 확인을 위한 서류 제출
+2. 서류 검토 과정을 거치는 것
+3. 고객님의 신원 확인 절차를 진행하는 것
+4. 모든 절차가 완료되면 계좌 개설이 가능합니다.
+
+계좌 개설을 원하시는 경우, 신분증과 함께 방문해 주시면 됩니다.
+    """},
+]
+
+# Tokenize and Generate Response
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to('cuda')
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=500,
+    do_sample=True,
+)
+
+# Decode and Print the Translation
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+```

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+---
+# FINGU-AI/L3-78b-Large-v1
+
+## Overview
+`FINGU-AI/L3-78b-Large-v1` is a powerful causal language model designed for a variety of natural language processing (NLP) tasks, including machine translation, text generation, and chat-based applications. This model is particularly useful for translating between languages, as well as supporting other custom NLP tasks through flexible input.
+
+## Example Usage
+
+### Installation
+Make sure to install the required packages:
+
+```bash
+pip install torch transformers
+```
+### Loading the Model
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Model and Tokenizer
+model_id = 'FINGU-AI/L3-78b-Large-v1'
+model = AutoModelForCausalLM.from_pretrained(model_id, attn_implementation="sdpa", torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model.to('cuda')
+
+# Input Messages for Translation
+messages = [
+    {"role": "system", "content": "translate korean to Uzbek"},
+    {"role": "user", "content": """새로운 은행 계좌를 개설하는 절차는 다음과 같습니다:
+
+1. 계좌 개설 목적과 신분 확인을 위한 서류 제출
+2. 서류 검토 과정을 거치는 것
+3. 고객님의 신원 확인 절차를 진행하는 것
+4. 모든 절차가 완료되면 계좌 개설이 가능합니다.
+
+계좌 개설을 원하시는 경우, 신분증과 함께 방문해 주시면 됩니다.
+    """},
+]
+
+# Tokenize and Generate Response
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to('cuda')
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=500,
+    do_sample=True,
+)
+
+# Decode and Print the Translation
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "newsbang/Homer-calme-2.4-78b-mix",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 86,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

model-00001-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1721ed907860da52d7e76d46a1b614395193a91842d82a5ff216c33a7a675eef
+size 2484568192

model-00002-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:831476c2f9081e2750d9052730d34263ca5e07265879468a79e3865b0f69f8ff
+size 3954707368

model-00003-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63fea801ca4aebca7b6fb1c362e945c91c06c341c6fd105dfe82f6fb109be36
+size 3795989864

model-00004-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d4871c48ca2f894bd5fe889c13e19fd49abf10c8f0e11924af26c55c0bc34c
+size 3995183944

model-00005-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e906fe492521e73cfaae8d141bddfa432b831e0271c5804e69282a0c69de3d9e
+size 3995183936

model-00006-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3bcbc09b10576318dcbfa5cfa39446a994c805a61375162f7cfe29d0959db9a
+size 3995202592

model-00007-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db5b78343c76375aaabcaaab205da9f8ed70191b6a7d95ba280fa3e0a77a92e
+size 3812767208

model-00008-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e9622986c826616b9edbac11ef725fa735d412eb2935fea46267c290d75ec5
+size 3995183936

model-00009-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77b71de9ddcb7fc61f8da9337ccb81e3c88096352dd5e5ebb80e533fcea6c9c
+size 3995183936

model-00010-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdbdae4d82c0679f1d930ac5444fa550e5e55b51db3b982f5da13c9c1d133732
+size 3995202592

model-00011-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b908551ba99358ed45095f7ca0fbbd745cc596c19ae6faa0fe34ecff024cb52
+size 3812767208

model-00012-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5545c98e2676e59ec64e354bc21c23c724185b49173c83088b8c645851e5b85f
+size 3995183944

model-00013-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60c242711a062c6719bd9614de66757224969ac800426d87af944b17f77d3af
+size 3995183928

model-00014-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e71cbe470bd1d66705de26495234a97e3178540193d9c93ef4be56338a814b3
+size 3995202592

model-00015-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8652ebd391cc489bac7bca0d1270582560fe0c0e436c7a1f7a7830493513880f
+size 3812767208

model-00016-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:710214cc01adb2398d029d72404c1069b5096415c53a2d900f64b3f389d4efe9
+size 3995183944

model-00017-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85493a8bce10043be398893790ba6c5f50727cf5aa5e16b1ee53972f77e20ea3
+size 3995183936

model-00018-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95fb1c11dd8fb93a65a7eea9205b5307dd329f78075f14826755ca13f3cf693
+size 3995202584

model-00019-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2db21eedf6cfbf1abb7f8594d1724b8a3fb9c190297a5684098b592b136d20c
+size 3812767208

model-00020-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ebbc84bb1c7b1b7ba979d954032d7f078e28063079e2bb82d3a0170af9d57b
+size 3995183944

model-00021-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c76484d2e62e4c7ee6ed20fe7b14e8d516ae2c33294c75db90a593d1ce71dc4
+size 3995183936

model-00022-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe10a679d771fd76918089972e63343f1b3212ec7a6823401f5b68ccef5d9fb6
+size 3995202584

model-00023-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16e989b3cf3f0b07805492b9e7a940adc4dcbbcd5ecff745d630d3c5db297df
+size 3812767200

model-00024-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097d9067c97d9aa22e1ed6dd2e3d806faf781aa060a6a6180a1ff35dbb961551
+size 3995183944

model-00025-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a38b3c4153f6d3b2627afd77854c43cfed2cb3193f778db1f5ed667d73e13b94
+size 3995183936

model-00026-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556612e7d1bef4eec3dcb557848e08b0a0da4521b686fa0464a59501923060b5
+size 3995202592

model-00027-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4a8adbed4a90d71d6f8627441fcd893c4b62a757ac6b47f6cc1a8b35ac0ac0
+size 3812767192

model-00028-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3707b3d03c0d4763b7c52bc91d95d8451278348843024e407d25e1fe039c4bd2
+size 3995183944

model-00029-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fabb5351914e4c4b65b7f410aaa9959265db19924732ad91bb44722cd9522846
+size 3995183936

model-00030-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a361f3bfafd728dd005296d6b3a4d07f66c58cd1487dadf231e3f92ec6290199
+size 3995202592

model-00031-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4224676866969780a9989cdee45b86523152999437f6246401efef0673a2525
+size 3812767208

model-00032-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a439ac65d64461b22e385ed2257588a98605723078e20161a41ee6d0e7fb5b2
+size 3995183936

model-00033-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0869a2b2edcebf31dd873f8ffa41555b74eaf92053af542cb90d14a83553178
+size 3995183936

model-00034-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f544f1d3c60b1e26cbb964d828910fea3a36086c873e612a7a99164a1faa7543
+size 3995202592

model-00035-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b548564e542f3983523bf9171595296a1601f3a9a15c1443b5c6b058a82993b
+size 3812767208

model-00036-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1ded1f30afcde2aab588121ac38296edc927f384569030b6ee6e0357672f29
+size 3995183944

model-00037-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ecf41a5c4c2d4b10843ad023e86fdca493191af8e683b4d20703801fd1c638a
+size 3995183928

model-00038-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24122ef0ea0bf95965e1a46ec3c6197f13f3069d5f58ca9e26c3ddc264b484ba
+size 3995202592

model-00039-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d6f6aa2ed8789cf180a1145aa1735368f3ca6ac5ab59601d6fe921e81ce068
+size 3812767208

model-00040-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cacd3d2dfcce755fe70a44f15496fc82d95a1d9a2cd297f152227d410e4a2e3e
+size 3510741688

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 155930927104}, "weight_map": {"lm_head.weight": "model-00001-of-00040.safetensors", "model.embed_tokens.weight": "model-00002-of-00040.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00040.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00040.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00040.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00040.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00040.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00040.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00040.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00040.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00040.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00040.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00040.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00040.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00040.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00040.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00040.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00040.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00040.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00040.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00040.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00040.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00040.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00040.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00040.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00040.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00040.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00040.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00040.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00040.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00040.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00040.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00040.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00040.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00040.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00040.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00040.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00040.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00040.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00040.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00040.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00040.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00040.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00040.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00040.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00040.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00040.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00040.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00040.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00040.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00040.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00040.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00040.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00040.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00040.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00040.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00040.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00040.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00040.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00040.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00040.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00040.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00040.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00040.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00040.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00040.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00040.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00040.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00040.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00040.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00040.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00040.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00040.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00040.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00040.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00040.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00040.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00040.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00040.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00040.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00040.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00040.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00040.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00040.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00040.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00040.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00040.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00040.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00040.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00040.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00040.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00040.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00040.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00040.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00040.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00040.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00040.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00040.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00040.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00040.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00040.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00040.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00040.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00040.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00040.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00040.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00040.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00040.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00040.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00040.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00040.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00040.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00040.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00040.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00040.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00040.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00040.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00040.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00040.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00040.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00040.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00040.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00040.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00040.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00040.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00040.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00040.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00040.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00040.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00040.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00040.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00040.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00040.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00040.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00040.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00040.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00040.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00040.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00040.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00040.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00040.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00040.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00040.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00040.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00040.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00040.safetensors", "model.layers.2.input_layernorm.weight": "model-00007-of-00040.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00040.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00040.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00040.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00040.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00008-of-00040.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00040.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00040.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00008-of-00040.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00040.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00008-of-00040.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00040.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00040.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00040.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00040.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00040.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00040.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00008-of-00040.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00040.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00040.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00008-of-00040.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00040.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00008-of-00040.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00040.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00040.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00040.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00040.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00040.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00040.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00009-of-00040.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00040.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00040.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00009-of-00040.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00040.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00009-of-00040.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00040.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00040.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00009-of-00040.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00040.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00009-of-00040.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00040.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00009-of-00040.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00040.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00040.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00009-of-00040.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00040.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00009-of-00040.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00040.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00040.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00040.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00040.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00040.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00040.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00010-of-00040.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00040.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00040.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00010-of-00040.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00040.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00010-of-00040.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00040.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00040.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00010-of-00040.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00040.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00040.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00040.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00010-of-00040.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00040.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00040.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00010-of-00040.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00040.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00010-of-00040.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00040.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00040.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00040.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00040.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00040.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00040.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00010-of-00040.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00040.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00040.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00011-of-00040.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00040.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00011-of-00040.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00040.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00040.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00040.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00040.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00040.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00040.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00011-of-00040.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00040.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00040.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00011-of-00040.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00040.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00011-of-00040.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00040.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00040.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00040.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00040.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00011-of-00040.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00040.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00011-of-00040.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00040.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00040.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00011-of-00040.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00040.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00011-of-00040.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00040.safetensors", "model.layers.28.input_layernorm.weight": "model-00011-of-00040.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00040.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00040.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00012-of-00040.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00040.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00012-of-00040.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00040.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00040.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00012-of-00040.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00040.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00012-of-00040.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00040.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00040.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00012-of-00040.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00040.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00012-of-00040.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00040.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00012-of-00040.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00040.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00040.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00012-of-00040.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00040.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00012-of-00040.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00040.safetensors", "model.layers.3.input_layernorm.weight": "model-00012-of-00040.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00012-of-00040.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00040.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00013-of-00040.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00040.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00013-of-00040.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00040.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00040.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00013-of-00040.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00040.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00013-of-00040.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00040.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00040.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00040.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00040.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00013-of-00040.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00040.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00013-of-00040.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00040.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00040.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00013-of-00040.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00040.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00013-of-00040.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00040.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00040.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00013-of-00040.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00040.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00014-of-00040.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00040.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00014-of-00040.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00040.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00040.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00014-of-00040.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00040.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00014-of-00040.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00040.safetensors", "model.layers.32.input_layernorm.weight": "model-00014-of-00040.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00014-of-00040.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00040.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00014-of-00040.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00040.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00014-of-00040.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00040.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00040.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00014-of-00040.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00040.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00014-of-00040.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00040.safetensors", "model.layers.33.input_layernorm.weight": "model-00014-of-00040.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00014-of-00040.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00014-of-00040.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00014-of-00040.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00040.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00014-of-00040.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00040.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00040.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00015-of-00040.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00040.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00015-of-00040.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00040.safetensors", "model.layers.34.input_layernorm.weight": "model-00015-of-00040.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00015-of-00040.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00040.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00015-of-00040.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00040.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00015-of-00040.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00040.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00040.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00015-of-00040.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00040.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00015-of-00040.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00040.safetensors", "model.layers.35.input_layernorm.weight": "model-00015-of-00040.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00015-of-00040.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00015-of-00040.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00015-of-00040.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00015-of-00040.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00015-of-00040.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00015-of-00040.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00040.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00015-of-00040.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00040.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00015-of-00040.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00040.safetensors", "model.layers.36.input_layernorm.weight": "model-00015-of-00040.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00016-of-00040.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00016-of-00040.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00016-of-00040.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00040.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00016-of-00040.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00040.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00040.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00016-of-00040.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00016-of-00040.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00016-of-00040.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00016-of-00040.safetensors", "model.layers.37.input_layernorm.weight": "model-00016-of-00040.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00016-of-00040.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00040.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00016-of-00040.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00040.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00016-of-00040.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00040.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00040.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00016-of-00040.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00040.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00016-of-00040.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00040.safetensors", "model.layers.38.input_layernorm.weight": "model-00016-of-00040.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00016-of-00040.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00040.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00017-of-00040.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00040.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00017-of-00040.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00040.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00040.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00017-of-00040.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00040.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00017-of-00040.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00040.safetensors", "model.layers.39.input_layernorm.weight": "model-00017-of-00040.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00017-of-00040.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00040.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00017-of-00040.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00040.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00017-of-00040.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00017-of-00040.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00040.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00017-of-00040.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00017-of-00040.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00017-of-00040.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00017-of-00040.safetensors", "model.layers.4.input_layernorm.weight": "model-00017-of-00040.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00017-of-00040.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00017-of-00040.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00018-of-00040.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00040.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00018-of-00040.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00018-of-00040.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00018-of-00040.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00018-of-00040.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00040.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00018-of-00040.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00018-of-00040.safetensors", "model.layers.40.input_layernorm.weight": "model-00018-of-00040.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00018-of-00040.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00018-of-00040.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00018-of-00040.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00040.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00018-of-00040.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00018-of-00040.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00018-of-00040.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00018-of-00040.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00040.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00018-of-00040.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00018-of-00040.safetensors", "model.layers.41.input_layernorm.weight": "model-00018-of-00040.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00018-of-00040.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00018-of-00040.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00018-of-00040.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00040.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00018-of-00040.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00040.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00040.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00019-of-00040.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00040.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00019-of-00040.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00040.safetensors", "model.layers.42.input_layernorm.weight": "model-00019-of-00040.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00019-of-00040.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00019-of-00040.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00019-of-00040.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00019-of-00040.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00019-of-00040.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00040.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00040.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00019-of-00040.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00040.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00019-of-00040.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00040.safetensors", "model.layers.43.input_layernorm.weight": "model-00019-of-00040.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00019-of-00040.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00019-of-00040.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00019-of-00040.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00019-of-00040.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00019-of-00040.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00040.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00019-of-00040.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00019-of-00040.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00040.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00019-of-00040.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00040.safetensors", "model.layers.44.input_layernorm.weight": "model-00019-of-00040.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00020-of-00040.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00020-of-00040.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00020-of-00040.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00020-of-00040.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00020-of-00040.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00020-of-00040.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00040.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00020-of-00040.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00020-of-00040.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00020-of-00040.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00020-of-00040.safetensors", "model.layers.45.input_layernorm.weight": "model-00020-of-00040.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00020-of-00040.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00020-of-00040.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00020-of-00040.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00020-of-00040.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00020-of-00040.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00020-of-00040.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00040.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00020-of-00040.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00020-of-00040.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00020-of-00040.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00020-of-00040.safetensors", "model.layers.46.input_layernorm.weight": "model-00020-of-00040.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00020-of-00040.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00021-of-00040.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00021-of-00040.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00021-of-00040.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00021-of-00040.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00021-of-00040.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00021-of-00040.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00021-of-00040.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00021-of-00040.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00021-of-00040.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00040.safetensors", "model.layers.47.input_layernorm.weight": "model-00021-of-00040.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00021-of-00040.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00021-of-00040.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00021-of-00040.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00021-of-00040.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00021-of-00040.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00021-of-00040.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00021-of-00040.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00021-of-00040.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00021-of-00040.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00021-of-00040.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00021-of-00040.safetensors", "model.layers.48.input_layernorm.weight": "model-00021-of-00040.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00021-of-00040.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00021-of-00040.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00022-of-00040.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00022-of-00040.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00022-of-00040.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00022-of-00040.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00022-of-00040.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00022-of-00040.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00022-of-00040.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00022-of-00040.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00022-of-00040.safetensors", "model.layers.49.input_layernorm.weight": "model-00022-of-00040.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00022-of-00040.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00022-of-00040.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00022-of-00040.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00022-of-00040.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00022-of-00040.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00022-of-00040.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00022-of-00040.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00022-of-00040.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00022-of-00040.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00022-of-00040.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00022-of-00040.safetensors", "model.layers.5.input_layernorm.weight": "model-00022-of-00040.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00022-of-00040.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00022-of-00040.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00022-of-00040.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00022-of-00040.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00022-of-00040.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00023-of-00040.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00023-of-00040.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00023-of-00040.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00040.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00023-of-00040.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00023-of-00040.safetensors", "model.layers.50.input_layernorm.weight": "model-00023-of-00040.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00023-of-00040.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00023-of-00040.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00023-of-00040.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00023-of-00040.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00023-of-00040.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00023-of-00040.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00023-of-00040.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00023-of-00040.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00023-of-00040.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00023-of-00040.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00023-of-00040.safetensors", "model.layers.51.input_layernorm.weight": "model-00023-of-00040.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00023-of-00040.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00023-of-00040.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00023-of-00040.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00023-of-00040.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00023-of-00040.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00023-of-00040.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00023-of-00040.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00023-of-00040.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00023-of-00040.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00023-of-00040.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00023-of-00040.safetensors", "model.layers.52.input_layernorm.weight": "model-00023-of-00040.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00024-of-00040.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00024-of-00040.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00024-of-00040.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00024-of-00040.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00024-of-00040.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00024-of-00040.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00024-of-00040.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00024-of-00040.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00024-of-00040.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00024-of-00040.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00024-of-00040.safetensors", "model.layers.53.input_layernorm.weight": "model-00024-of-00040.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00024-of-00040.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00024-of-00040.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00024-of-00040.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00024-of-00040.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00024-of-00040.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00024-of-00040.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00024-of-00040.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00024-of-00040.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00024-of-00040.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00024-of-00040.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00024-of-00040.safetensors", "model.layers.54.input_layernorm.weight": "model-00024-of-00040.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00024-of-00040.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00025-of-00040.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00025-of-00040.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00025-of-00040.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00025-of-00040.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00025-of-00040.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00025-of-00040.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00025-of-00040.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00025-of-00040.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00025-of-00040.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00025-of-00040.safetensors", "model.layers.55.input_layernorm.weight": "model-00025-of-00040.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00025-of-00040.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00025-of-00040.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00025-of-00040.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00025-of-00040.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00025-of-00040.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00025-of-00040.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00025-of-00040.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00025-of-00040.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00025-of-00040.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00025-of-00040.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00025-of-00040.safetensors", "model.layers.56.input_layernorm.weight": "model-00025-of-00040.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00025-of-00040.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00025-of-00040.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00026-of-00040.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00026-of-00040.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00026-of-00040.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00026-of-00040.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00026-of-00040.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00026-of-00040.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00026-of-00040.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00026-of-00040.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00026-of-00040.safetensors", "model.layers.57.input_layernorm.weight": "model-00026-of-00040.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00026-of-00040.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00026-of-00040.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00026-of-00040.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00026-of-00040.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00026-of-00040.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00026-of-00040.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00026-of-00040.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00026-of-00040.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00026-of-00040.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00026-of-00040.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00026-of-00040.safetensors", "model.layers.58.input_layernorm.weight": "model-00026-of-00040.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00026-of-00040.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00026-of-00040.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00026-of-00040.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00026-of-00040.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00026-of-00040.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00027-of-00040.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00027-of-00040.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00027-of-00040.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00027-of-00040.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00027-of-00040.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00027-of-00040.safetensors", "model.layers.59.input_layernorm.weight": "model-00027-of-00040.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00027-of-00040.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00027-of-00040.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00027-of-00040.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00027-of-00040.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00027-of-00040.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00027-of-00040.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00027-of-00040.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00027-of-00040.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00027-of-00040.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00027-of-00040.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00027-of-00040.safetensors", "model.layers.6.input_layernorm.weight": "model-00027-of-00040.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00027-of-00040.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00027-of-00040.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00027-of-00040.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00027-of-00040.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00027-of-00040.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00027-of-00040.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00027-of-00040.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00027-of-00040.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00027-of-00040.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00027-of-00040.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00027-of-00040.safetensors", "model.layers.60.input_layernorm.weight": "model-00027-of-00040.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00028-of-00040.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00028-of-00040.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00028-of-00040.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00028-of-00040.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00028-of-00040.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00028-of-00040.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00028-of-00040.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00028-of-00040.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00028-of-00040.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00028-of-00040.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00028-of-00040.safetensors", "model.layers.61.input_layernorm.weight": "model-00028-of-00040.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00028-of-00040.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00028-of-00040.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00028-of-00040.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00028-of-00040.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00028-of-00040.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00028-of-00040.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00028-of-00040.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00028-of-00040.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00028-of-00040.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00028-of-00040.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00028-of-00040.safetensors", "model.layers.62.input_layernorm.weight": "model-00028-of-00040.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00028-of-00040.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00029-of-00040.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00029-of-00040.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00029-of-00040.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00029-of-00040.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00029-of-00040.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00029-of-00040.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00029-of-00040.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00029-of-00040.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00029-of-00040.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00029-of-00040.safetensors", "model.layers.63.input_layernorm.weight": "model-00029-of-00040.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00029-of-00040.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00029-of-00040.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00029-of-00040.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00029-of-00040.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00029-of-00040.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00029-of-00040.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00029-of-00040.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00029-of-00040.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00029-of-00040.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00029-of-00040.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00029-of-00040.safetensors", "model.layers.64.input_layernorm.weight": "model-00029-of-00040.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00029-of-00040.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00029-of-00040.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00030-of-00040.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00030-of-00040.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00030-of-00040.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00030-of-00040.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00030-of-00040.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00030-of-00040.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00030-of-00040.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00030-of-00040.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00030-of-00040.safetensors", "model.layers.65.input_layernorm.weight": "model-00030-of-00040.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00030-of-00040.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00030-of-00040.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00030-of-00040.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00030-of-00040.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00030-of-00040.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00030-of-00040.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00030-of-00040.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00030-of-00040.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00030-of-00040.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00030-of-00040.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00030-of-00040.safetensors", "model.layers.66.input_layernorm.weight": "model-00030-of-00040.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00030-of-00040.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00030-of-00040.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00030-of-00040.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00030-of-00040.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00030-of-00040.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00031-of-00040.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00031-of-00040.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00031-of-00040.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00031-of-00040.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00031-of-00040.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00031-of-00040.safetensors", "model.layers.67.input_layernorm.weight": "model-00031-of-00040.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00031-of-00040.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00031-of-00040.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00031-of-00040.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00031-of-00040.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00031-of-00040.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00031-of-00040.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00031-of-00040.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00031-of-00040.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00031-of-00040.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00031-of-00040.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00031-of-00040.safetensors", "model.layers.68.input_layernorm.weight": "model-00031-of-00040.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00031-of-00040.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00031-of-00040.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00031-of-00040.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00031-of-00040.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00031-of-00040.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00031-of-00040.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00031-of-00040.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00031-of-00040.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00031-of-00040.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00031-of-00040.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00031-of-00040.safetensors", "model.layers.69.input_layernorm.weight": "model-00031-of-00040.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00032-of-00040.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00032-of-00040.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00032-of-00040.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00032-of-00040.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00032-of-00040.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00032-of-00040.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00032-of-00040.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00032-of-00040.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00032-of-00040.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00032-of-00040.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00032-of-00040.safetensors", "model.layers.7.input_layernorm.weight": "model-00032-of-00040.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00032-of-00040.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00032-of-00040.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00032-of-00040.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00032-of-00040.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00032-of-00040.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00032-of-00040.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00032-of-00040.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00032-of-00040.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00032-of-00040.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00032-of-00040.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00032-of-00040.safetensors", "model.layers.70.input_layernorm.weight": "model-00032-of-00040.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00032-of-00040.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00033-of-00040.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00033-of-00040.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00033-of-00040.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00033-of-00040.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00033-of-00040.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00033-of-00040.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00033-of-00040.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00033-of-00040.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00033-of-00040.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00033-of-00040.safetensors", "model.layers.71.input_layernorm.weight": "model-00033-of-00040.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00033-of-00040.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00033-of-00040.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00033-of-00040.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00033-of-00040.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00033-of-00040.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00033-of-00040.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00033-of-00040.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00033-of-00040.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00033-of-00040.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00033-of-00040.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00033-of-00040.safetensors", "model.layers.72.input_layernorm.weight": "model-00033-of-00040.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00033-of-00040.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00033-of-00040.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00034-of-00040.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00034-of-00040.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00034-of-00040.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00034-of-00040.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00034-of-00040.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00034-of-00040.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00034-of-00040.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00034-of-00040.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00034-of-00040.safetensors", "model.layers.73.input_layernorm.weight": "model-00034-of-00040.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00034-of-00040.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00034-of-00040.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00034-of-00040.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00034-of-00040.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00034-of-00040.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00034-of-00040.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00034-of-00040.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00034-of-00040.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00034-of-00040.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00034-of-00040.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00034-of-00040.safetensors", "model.layers.74.input_layernorm.weight": "model-00034-of-00040.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00034-of-00040.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00034-of-00040.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00034-of-00040.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00034-of-00040.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00034-of-00040.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00035-of-00040.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00035-of-00040.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00035-of-00040.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00035-of-00040.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00035-of-00040.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00035-of-00040.safetensors", "model.layers.75.input_layernorm.weight": "model-00035-of-00040.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00035-of-00040.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00035-of-00040.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00035-of-00040.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00035-of-00040.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00035-of-00040.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00035-of-00040.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00035-of-00040.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00035-of-00040.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00035-of-00040.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00035-of-00040.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00035-of-00040.safetensors", "model.layers.76.input_layernorm.weight": "model-00035-of-00040.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00035-of-00040.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00035-of-00040.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00035-of-00040.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00035-of-00040.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00035-of-00040.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00035-of-00040.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00035-of-00040.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00035-of-00040.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00035-of-00040.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00035-of-00040.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00035-of-00040.safetensors", "model.layers.77.input_layernorm.weight": "model-00035-of-00040.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00036-of-00040.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00036-of-00040.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00036-of-00040.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00036-of-00040.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00036-of-00040.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00036-of-00040.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00036-of-00040.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00036-of-00040.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00036-of-00040.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00036-of-00040.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00036-of-00040.safetensors", "model.layers.78.input_layernorm.weight": "model-00036-of-00040.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00036-of-00040.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00036-of-00040.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00036-of-00040.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00036-of-00040.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00036-of-00040.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00036-of-00040.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00036-of-00040.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00036-of-00040.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00036-of-00040.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00036-of-00040.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00036-of-00040.safetensors", "model.layers.79.input_layernorm.weight": "model-00036-of-00040.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00036-of-00040.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00037-of-00040.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00037-of-00040.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00037-of-00040.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00037-of-00040.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00037-of-00040.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00037-of-00040.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00037-of-00040.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00037-of-00040.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00037-of-00040.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00037-of-00040.safetensors", "model.layers.8.input_layernorm.weight": "model-00037-of-00040.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00037-of-00040.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00037-of-00040.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00037-of-00040.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00037-of-00040.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00037-of-00040.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00037-of-00040.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00037-of-00040.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00037-of-00040.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00037-of-00040.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00037-of-00040.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00037-of-00040.safetensors", "model.layers.80.input_layernorm.weight": "model-00037-of-00040.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00037-of-00040.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00037-of-00040.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00038-of-00040.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00038-of-00040.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00038-of-00040.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00038-of-00040.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00038-of-00040.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00038-of-00040.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00038-of-00040.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00038-of-00040.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00038-of-00040.safetensors", "model.layers.81.input_layernorm.weight": "model-00038-of-00040.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00038-of-00040.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00038-of-00040.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00038-of-00040.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00038-of-00040.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00038-of-00040.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00038-of-00040.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00038-of-00040.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00038-of-00040.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00038-of-00040.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00038-of-00040.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00038-of-00040.safetensors", "model.layers.82.input_layernorm.weight": "model-00038-of-00040.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00038-of-00040.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00038-of-00040.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00038-of-00040.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00038-of-00040.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00038-of-00040.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00039-of-00040.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00039-of-00040.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00039-of-00040.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00039-of-00040.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00039-of-00040.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00039-of-00040.safetensors", "model.layers.83.input_layernorm.weight": "model-00039-of-00040.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00039-of-00040.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00039-of-00040.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00039-of-00040.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00039-of-00040.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00039-of-00040.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00039-of-00040.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00039-of-00040.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00039-of-00040.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00039-of-00040.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00039-of-00040.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00039-of-00040.safetensors", "model.layers.84.input_layernorm.weight": "model-00039-of-00040.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00039-of-00040.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00039-of-00040.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00039-of-00040.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00039-of-00040.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00039-of-00040.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00039-of-00040.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00039-of-00040.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00039-of-00040.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00039-of-00040.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00039-of-00040.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00039-of-00040.safetensors", "model.layers.85.input_layernorm.weight": "model-00039-of-00040.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00040-of-00040.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00040-of-00040.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00040-of-00040.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00040-of-00040.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00040-of-00040.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00040-of-00040.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00040-of-00040.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00040-of-00040.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00040-of-00040.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00040-of-00040.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00040-of-00040.safetensors", "model.layers.9.input_layernorm.weight": "model-00040-of-00040.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00040-of-00040.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00040-of-00040.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00040-of-00040.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00040-of-00040.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00040-of-00040.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00040-of-00040.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00040-of-00040.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00040-of-00040.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00040-of-00040.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00040-of-00040.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00040-of-00040.safetensors", "model.norm.weight": "model-00040-of-00040.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}