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
+
+## Overview
+`FINGU-AI/L3-78b-Large` 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'
+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
+
+## Overview
+`FINGU-AI/L3-78b-Large` 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'
+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 +1,30 @@
+{
+  "_name_or_path": "dfurman/CalmeRys-78B-Orpo-v0.1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151644,
+  "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,
+  "pad_token_id": 151645,
+  "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 sha256:354fd4313ce80ab0e83b5dae319e7cdb803589699b4bc90160a613ec409cf313
+size 2484568192

model-00002-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3058e5f64427211bf5752fa6c6d6165a90be679cac3e7a7ab0385a608b8a068a
+size 3954707368

model-00003-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:867100cb979d2d0ca1cb6ca30ead743bac0cbd9da383b1771022c3d89982ffdc
+size 3795989864

model-00004-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3531912dba956a4d21d926d2ae6a4614bf0b135dc41dc09345c13f153ff3e5
+size 3995183944

model-00005-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7543c7a9e7038dd12d65fd83f25a510abd200e478871e546eecf291e806f96
+size 3995183936

model-00006-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a807ceac94366fc8e649b46da831bff4b0c7c11fe5f3175167cabe3ca87b13
+size 3995202592

model-00007-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ffd4dca4273a8f8f3aad53d5ccea3931912ce1fea6197f78bbb0541999c5b4c
+size 3812767208

model-00008-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab50a6c5dc1a5374a285671195a7aea5fc74f575f980d5c931a36364d520b346
+size 3995183936

model-00009-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94096f5e1fce2b394f0fa8532c074e553518cd92d3858c7833986fa25a140f7b
+size 3995183936

model-00010-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c492f8b39845cb8502cf90e7793df13515422d2ce7b074684b4216dea90ba21
+size 3995202592

model-00011-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9abff731640ed7b417512ae1cab3a173cbe097dc5a963fb38a06eaf9eb5b446
+size 3812767208

model-00012-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d120f8fc7d7109f60dc4522990c6540aecd9148d1cfcbd75dc7f5cd27e1c77ce
+size 3995183944

model-00013-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a55ec018f639a0e6cdbae3aedba8d41b739004710d01ac3f566d9c14d8f03c
+size 3995183928

model-00014-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02ba434d9672d68c4b52f27edcd0b54d31e71b514bb433ef2ad2524d1c8c22e
+size 3995202592

model-00015-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad17ece04c457345a57a138518e17c7bd19a59952ecae72dad2f8ca5b291e64c
+size 3812767208

model-00016-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:059927948f915b4b04f390cb4b50758e61d3835b706a3a9cdd87557de5fc3492
+size 3995183944

model-00017-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebac74d3520779f14412296a747466561e4221fb7195b0a8301bf003f9908fe2
+size 3995183936

model-00018-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4a9b7a15c9344625773ae0036d59e0c22bfe498fcac1fca7314cd2101ce6e1
+size 3995202584

model-00019-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92e82b81700c8f009af5d9a5a84a413b029d25eec18610b947501e6df96c327
+size 3812767208

model-00020-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccabd0209cc4abda193baaea07ccd88bff0392bf7e3910ec3f962a61d40bbca4
+size 3995183944

model-00021-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d6eaa5a4d42ba4a6ed1a0f4491e02b440bc5198b2b5be95914c85ed0ecbb4f
+size 3995183936

model-00022-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3a02edeefc1129443011c195b4af165660a7a2fa889dfd6fb741916ca606ab
+size 3995202584

model-00023-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b64adcb5d8d3d67ac9d249c0b7d858e17b6bb3f7ab18147d3136ee925420fe5
+size 3812767200

model-00024-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ce1c86cf98b773fb8c0b8b609acef33d09d12a1b641491015e626ddb00a450
+size 3995183944

model-00025-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd2553ec928a1daf2699fc53f5c60d496504efcb2b1f9a764df3d3f924e7a3a
+size 3995183936

model-00026-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f2bffeb3cf6f351d52bb081e542303e5685641f4ccb6fbd5abb0a3f9e905e0
+size 3995202592

model-00027-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f923b4d2044bf588093f4f4284d24e47d80b7767836b9244c676822d8e5945
+size 3812767192

model-00028-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eeb0c243bf98246fb0454bfd9835cded2753396cb6fc0b7f63e85afef303c2d
+size 3995183944

model-00029-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2810144e753daf191e512f212e1da2a556aff5ce5927d378cd72174567390a9e
+size 3995183936

model-00030-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:811b731f49ef4985428cef61ac5a739b1cae7f5e35a412b0eafbdeff5ba531c1
+size 3995202592

model-00031-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bacffe8ddf1eb5cc0e2fe80513df8ac0e6c39756372acc5e0175a6e2f18922b8
+size 3812767208

model-00032-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168dc04e91d7416053bdddf87c5f82931332ccf8a037f5fb36234611fc9bb2f8
+size 3995183936

model-00033-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5a4357e098f6572a580f55722d1f5b1ca6627a30579860b7debda1a70eaf88
+size 3995183936

model-00034-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08203a51de9ae8ed2f19261e6ca91dba88ea10035c9afdef866eb249c73adda7
+size 3995202592

model-00035-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f5611e79f81a808c6849cd950a3cf71c3e0da0c2a6863a124df74de52e1c96
+size 3812767208

model-00036-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8491a7547601f53db4ed550f57063b8c3b487fd1988eab39d9d22bf736c005d
+size 3995183944

model-00037-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be3ed4bb9b3a6fdf1209c7d5b800f6ea33beecc8e7dea209698c3d585b6c04c
+size 3995183928

model-00038-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e631811b3f8d486a02560776fd4c4aa060d46ebffa7d6abc76f58f6d98bb199
+size 3995202592

model-00039-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a5c8b68f8033f2ad81b3b45c350bfb1324a53206f9e87942ed9fc95801031c
+size 3812767208

model-00040-of-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5d12ccc7efb5a2b7d65896d856409c6ccecc613e53270ba19a7d47404dd864
+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 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "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": "<|im_start|>",
+  "chat_template": "{% 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": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}