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 +1,60 @@
+---
+license: llama3.1
+---
+# FINGU-AI/L3-72b-Large
+
+## Overview
+`FINGU-AI/L3-72b-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/L3-72b-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 +1,60 @@
+---
+license: llama3.1
+---
+# FINGU-AI/L3-72b-Large
+
+## Overview
+`FINGU-AI/L3-72b-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/L3-72b-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 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Sakalti/ultiima-72B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187d946bbae7b92cd4f604e3aee5af023d994aaf934d8728f48139dd58e54a3a
+size 2491416704

model-00002-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94117ae7f14d8903486c7b2e65ea3e0140672acc3140de7c06c5d80f7f9ba38a
+size 3961555880

model-00003-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22e81637b8e8f74bf87a23920afeda750611a5d2abf10adf7fd55b288c73c5f
+size 3795989864

model-00004-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c8f6e7a2f2e26d0ebf7da35c1fa7d837258cd7d3ff5f68c90df858b05a9fa2c
+size 3995183944

model-00005-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1a1eb2bb34af535e97c7c222aec48391ea98b3efe69add54c88937c0c2579e
+size 3995183936

model-00006-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c9256685c8b778d9a24348e15cc846d038a67500cf878a5f6c4cbca9230858
+size 3995202592

model-00007-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7cfea22e1a5a665009989efae59ed3554c20617a9e55440ac1356ed2dc603a8
+size 3812767208

model-00008-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba760df594b4ef07c1ad21b6be2b5d39f3465376a1ea4c8ca872db70f9e4b1e
+size 3995183936

model-00009-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa3f52da483a2438dfb33adbfc6c9a22cc0686df2536006f1865abda874186d
+size 3995183936

model-00010-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5961511c7ce381d8b4f27855f35e6db8271a27a365e9ba9910c43e86398c7f
+size 3995202592

model-00011-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ac458c1f3aaffbc305a64eec57fc320dcf5d4ecd7a49f5b0fe1dde6d0f788f
+size 3812767208

model-00012-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb546161c332936e7d09d2efbdb819f305db35da1ea184eee0d144fbf7601ff
+size 3995183944

model-00013-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92efad62b869fcbc8bd8857f2f75a85f37f3ce22a82a516f1ac1de7e5067a696
+size 3995183928

model-00014-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2828d1e7ca2669b2f9f3c03248ec6fd2fa3477405bb8c09eb0cd120fbee1f00
+size 3995202592

model-00015-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deec21c7fd3d3045e31c918048b2f270ec7296f9a1d0140a9e7b53a8b97a4581
+size 3812767208

model-00016-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950552ae3dd133d023a02e4cdbfb213b6c9a95abf423c2bd469db135e545dee2
+size 3995183944

model-00017-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c97eec3c7fe2ede5c8fc082f2b3b3016758a2b04f0dbbb20db17a63f223abf1
+size 3995183936

model-00018-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b507dadf47c003ce12303e9bcbe3cd6e40810852a95cbf6c411b5e5bafad06ca
+size 3995202584

model-00019-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8683f910165ae9d17432455395e91451eaa5e888ecfb383c88e877af63440a39
+size 3812767208

model-00020-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ca685ca8eb2995b268ca787e953a3454d5f16a7e3558a5ec99d8e76dc2caa0
+size 3995183944

model-00021-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369fdef3f490db779f6a2a805770116a7e00ec0ecfbd27bcc1c8ed46787fa4fd
+size 3995183936

model-00022-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff90fb5924cf00c1b4594214a87a88822e8318baa7bac378fff98b549b1d796f
+size 3995202584

model-00023-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1d996815c53f1ca8d23893e27cf47fec6ac945007d58a568511b3376437e51
+size 3812767200

model-00024-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b20c36211b22cdabaca090dbe3566894b75067d6f2aa1b1a2e14ff132fc4dc
+size 3995183944

model-00025-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2709fd38b47649d294ce66dcf89a8fdd77617f74c9621461dcb46f37d30086
+size 3995183936

model-00026-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52859d6ec9ca923acd6eb387bb07ca38726fcf1d546be3dc4365a0178425e841
+size 3995202592

model-00027-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f75a0e0c9f2e73283c54d1b3898a367aebc64cc557eae2d45222320c2d6ff98
+size 3812767192

model-00028-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c23845036619865a4232e9ca1f165a4d30eb1128a67082f1dde23302a2fd7c4
+size 3995183944

model-00029-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc14c5ea6cda0a50b57a8c83afdf07facafb2a0233132bbe56cee13113cb1dc
+size 3995183936

model-00030-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5091d3907c6c264a5c0712c998fa19180bcff1d51f985f5364f9c7d103e298
+size 3995202592

model-00031-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809f8c56ec02ee5248789950bab03d4b4a91f9ca0688b21b813dc35438e76bee
+size 3812767208

model-00032-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e15a8aff9cbe85ec68e9170aee3dbb5d734d73eb038a6920cf40ff4e09a966c
+size 3995183936

model-00033-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a24a463c58a150a71a4ebcf183c78652f46c89d10d0774beb2b16d052882c9c
+size 3995183936

model-00034-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbbc5c8c39f990035b264ac105bf2f8d592bb6fcecdf1ce5a4a2c1306a91521
+size 3995202592

model-00035-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed334de9de95191199a13a487fed9413210e442f030b2a003914c293c2d7c842
+size 3812767208

model-00036-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e10e355dddf67b46ee4ad39315efb0a114927607bb84db8138e39b7bf8aa93
+size 3995183944

model-00037-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8429c536eb7d7a10b553149a5afcdfa127e526db4c0ddbb01d9d87d45a81f5b
+size 3995183928

model-00038-of-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5fdfdd6ae0f2920c191437e19dbf96d0e6c41e13588facdd12e81aadc6608a1
+size 786486376

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 145412407296}, "weight_map": {"lm_head.weight": "model-00001-of-00038.safetensors", "model.embed_tokens.weight": "model-00002-of-00038.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00038.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00038.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00038.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00038.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00038.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00038.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00038.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00038.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00038.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00038.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00038.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00038.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00038.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00038.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00038.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00038.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00038.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00038.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00038.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00038.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00038.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00038.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00038.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00038.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00038.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00038.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00038.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00038.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00038.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00038.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00038.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00038.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00038.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00038.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00038.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00038.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00038.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00038.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00038.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00038.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00038.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00038.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00038.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00038.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00038.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00038.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00038.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00038.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00038.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00038.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00038.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00038.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00038.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00038.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00038.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00038.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00038.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00038.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00038.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00038.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00038.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00038.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00038.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00038.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00038.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00038.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00038.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00038.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00038.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00038.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00038.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00038.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00038.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00038.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00038.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00038.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00038.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00038.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00038.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00038.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00038.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00038.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00038.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00038.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00038.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00038.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00038.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00038.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00038.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00038.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00038.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00038.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00038.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00038.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00038.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00038.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00038.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00038.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00038.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00038.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00038.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00038.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00038.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00038.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00038.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00038.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00038.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00038.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00038.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00038.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00038.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00038.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00038.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00038.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00038.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00038.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00038.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00038.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00038.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00038.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00038.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00038.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00038.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00038.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00038.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00038.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00038.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00038.safetensors", "model.layers.2.input_layernorm.weight": "model-00007-of-00038.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00038.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00038.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00038.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00038.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00008-of-00038.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00038.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00038.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00008-of-00038.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00038.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00008-of-00038.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00038.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00038.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00038.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00038.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00038.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00038.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00008-of-00038.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00038.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00038.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00008-of-00038.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00038.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00008-of-00038.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00038.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00038.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00038.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00038.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00038.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00038.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00009-of-00038.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00038.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00038.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00009-of-00038.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00038.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00009-of-00038.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00038.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00038.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00009-of-00038.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00038.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00009-of-00038.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00038.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00009-of-00038.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00038.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00038.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00009-of-00038.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00038.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00009-of-00038.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00038.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00038.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00038.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00038.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00038.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00038.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00010-of-00038.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00038.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00038.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00010-of-00038.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00038.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00010-of-00038.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00038.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00038.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00010-of-00038.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00038.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00038.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00038.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00010-of-00038.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00038.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00038.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00010-of-00038.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00038.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00010-of-00038.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00038.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00038.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00038.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00038.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00038.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00038.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00010-of-00038.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00038.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00038.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00011-of-00038.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00038.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00011-of-00038.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00038.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00038.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00038.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00038.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00038.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00038.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00011-of-00038.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00038.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00038.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00011-of-00038.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00038.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00011-of-00038.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00038.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00038.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00038.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00038.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00011-of-00038.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00038.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00011-of-00038.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00038.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00038.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00011-of-00038.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00038.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00011-of-00038.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00038.safetensors", "model.layers.28.input_layernorm.weight": "model-00011-of-00038.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00038.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00038.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00012-of-00038.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00038.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00012-of-00038.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00038.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00038.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00012-of-00038.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00038.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00012-of-00038.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00038.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00038.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00012-of-00038.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00038.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00012-of-00038.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00038.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00012-of-00038.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00038.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00038.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00012-of-00038.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00038.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00012-of-00038.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00038.safetensors", "model.layers.3.input_layernorm.weight": "model-00012-of-00038.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00012-of-00038.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00038.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00013-of-00038.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00038.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00013-of-00038.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00038.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00038.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00013-of-00038.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00038.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00013-of-00038.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00038.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00038.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00038.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00038.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00013-of-00038.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00038.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00013-of-00038.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00038.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00038.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00013-of-00038.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00038.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00013-of-00038.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00038.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00038.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00013-of-00038.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00038.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00014-of-00038.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00038.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00014-of-00038.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00038.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00038.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00014-of-00038.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00038.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00014-of-00038.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00038.safetensors", "model.layers.32.input_layernorm.weight": "model-00014-of-00038.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00014-of-00038.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00038.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00014-of-00038.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00038.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00014-of-00038.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00014-of-00038.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00014-of-00038.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00014-of-00038.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00014-of-00038.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00014-of-00038.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00014-of-00038.safetensors", "model.layers.33.input_layernorm.weight": "model-00014-of-00038.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00014-of-00038.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00014-of-00038.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00014-of-00038.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00038.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00014-of-00038.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00038.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00038.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00015-of-00038.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00038.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00015-of-00038.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00038.safetensors", "model.layers.34.input_layernorm.weight": "model-00015-of-00038.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00015-of-00038.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00038.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00015-of-00038.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00038.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00015-of-00038.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00038.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00038.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00015-of-00038.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00038.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00015-of-00038.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.input_layernorm.weight": "model-00015-of-00038.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00015-of-00038.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00015-of-00038.safetensors", "model.layers.36.input_layernorm.weight": "model-00015-of-00038.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00038.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00016-of-00038.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00016-of-00038.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00016-of-00038.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00016-of-00038.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00016-of-00038.safetensors", "model.layers.37.input_layernorm.weight": "model-00016-of-00038.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00016-of-00038.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00038.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00016-of-00038.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00016-of-00038.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00016-of-00038.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00016-of-00038.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00016-of-00038.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00016-of-00038.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00016-of-00038.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00016-of-00038.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00016-of-00038.safetensors", "model.layers.38.input_layernorm.weight": "model-00016-of-00038.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00016-of-00038.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00038.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00017-of-00038.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00038.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00017-of-00038.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00038.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00038.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00017-of-00038.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00038.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00017-of-00038.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00038.safetensors", "model.layers.39.input_layernorm.weight": "model-00017-of-00038.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00017-of-00038.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00038.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00017-of-00038.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00038.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00017-of-00038.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00017-of-00038.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00038.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00017-of-00038.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00017-of-00038.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00017-of-00038.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00017-of-00038.safetensors", "model.layers.4.input_layernorm.weight": "model-00017-of-00038.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00017-of-00038.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00017-of-00038.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00018-of-00038.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00038.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00018-of-00038.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00018-of-00038.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00018-of-00038.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00018-of-00038.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00038.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00018-of-00038.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00018-of-00038.safetensors", "model.layers.40.input_layernorm.weight": "model-00018-of-00038.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00018-of-00038.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00018-of-00038.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00018-of-00038.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00038.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00018-of-00038.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00018-of-00038.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00018-of-00038.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00018-of-00038.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00038.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00018-of-00038.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00018-of-00038.safetensors", "model.layers.41.input_layernorm.weight": "model-00018-of-00038.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00018-of-00038.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00018-of-00038.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00018-of-00038.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00038.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00018-of-00038.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00038.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00038.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00019-of-00038.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00038.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00019-of-00038.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00038.safetensors", "model.layers.42.input_layernorm.weight": "model-00019-of-00038.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00019-of-00038.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00019-of-00038.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00019-of-00038.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00019-of-00038.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00019-of-00038.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00038.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00019-of-00038.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00019-of-00038.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00038.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00019-of-00038.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00038.safetensors", "model.layers.43.input_layernorm.weight": "model-00019-of-00038.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00019-of-00038.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00019-of-00038.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00019-of-00038.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00019-of-00038.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00019-of-00038.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00038.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00019-of-00038.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00019-of-00038.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00038.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00019-of-00038.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00038.safetensors", "model.layers.44.input_layernorm.weight": "model-00019-of-00038.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00020-of-00038.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00020-of-00038.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00020-of-00038.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00020-of-00038.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00020-of-00038.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00020-of-00038.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00038.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00020-of-00038.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00020-of-00038.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00020-of-00038.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00020-of-00038.safetensors", "model.layers.45.input_layernorm.weight": "model-00020-of-00038.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00020-of-00038.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00020-of-00038.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00020-of-00038.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00020-of-00038.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00020-of-00038.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00020-of-00038.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00038.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00020-of-00038.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00020-of-00038.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00020-of-00038.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00020-of-00038.safetensors", "model.layers.46.input_layernorm.weight": "model-00020-of-00038.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00020-of-00038.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00021-of-00038.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00021-of-00038.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00021-of-00038.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00021-of-00038.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00021-of-00038.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00021-of-00038.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00021-of-00038.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00021-of-00038.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00021-of-00038.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.input_layernorm.weight": "model-00021-of-00038.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00021-of-00038.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00021-of-00038.safetensors", "model.layers.48.input_layernorm.weight": "model-00021-of-00038.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00021-of-00038.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00021-of-00038.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00022-of-00038.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00022-of-00038.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00022-of-00038.safetensors", "model.layers.49.input_layernorm.weight": "model-00022-of-00038.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00022-of-00038.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00022-of-00038.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00022-of-00038.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00022-of-00038.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00022-of-00038.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00022-of-00038.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00022-of-00038.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00022-of-00038.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00022-of-00038.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00022-of-00038.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00022-of-00038.safetensors", "model.layers.5.input_layernorm.weight": "model-00022-of-00038.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00022-of-00038.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00022-of-00038.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00022-of-00038.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00022-of-00038.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00022-of-00038.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00023-of-00038.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00023-of-00038.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00023-of-00038.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00038.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00023-of-00038.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00023-of-00038.safetensors", "model.layers.50.input_layernorm.weight": "model-00023-of-00038.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00023-of-00038.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00023-of-00038.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00023-of-00038.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00023-of-00038.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00023-of-00038.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00023-of-00038.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00023-of-00038.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00023-of-00038.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00023-of-00038.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00023-of-00038.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00023-of-00038.safetensors", "model.layers.51.input_layernorm.weight": "model-00023-of-00038.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00023-of-00038.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00023-of-00038.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00023-of-00038.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00023-of-00038.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00023-of-00038.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00023-of-00038.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00023-of-00038.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00023-of-00038.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00023-of-00038.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00023-of-00038.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00023-of-00038.safetensors", "model.layers.52.input_layernorm.weight": "model-00023-of-00038.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00024-of-00038.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00024-of-00038.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00024-of-00038.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00024-of-00038.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00024-of-00038.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00024-of-00038.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00024-of-00038.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00024-of-00038.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00024-of-00038.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00024-of-00038.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00024-of-00038.safetensors", "model.layers.53.input_layernorm.weight": "model-00024-of-00038.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00024-of-00038.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00024-of-00038.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00024-of-00038.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00024-of-00038.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00024-of-00038.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00024-of-00038.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00024-of-00038.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00024-of-00038.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00024-of-00038.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00024-of-00038.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00024-of-00038.safetensors", "model.layers.54.input_layernorm.weight": "model-00024-of-00038.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00024-of-00038.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00025-of-00038.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00025-of-00038.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00025-of-00038.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00025-of-00038.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00025-of-00038.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00025-of-00038.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00025-of-00038.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00025-of-00038.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00025-of-00038.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00025-of-00038.safetensors", "model.layers.55.input_layernorm.weight": "model-00025-of-00038.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00025-of-00038.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00025-of-00038.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00025-of-00038.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00025-of-00038.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00025-of-00038.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00025-of-00038.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00025-of-00038.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00025-of-00038.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00025-of-00038.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00025-of-00038.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00025-of-00038.safetensors", "model.layers.56.input_layernorm.weight": "model-00025-of-00038.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00025-of-00038.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00025-of-00038.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00026-of-00038.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00026-of-00038.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00026-of-00038.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00026-of-00038.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00026-of-00038.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00026-of-00038.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00026-of-00038.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00026-of-00038.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00026-of-00038.safetensors", "model.layers.57.input_layernorm.weight": "model-00026-of-00038.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00026-of-00038.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00026-of-00038.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00026-of-00038.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00026-of-00038.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00026-of-00038.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00026-of-00038.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00026-of-00038.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00026-of-00038.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00026-of-00038.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00026-of-00038.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00026-of-00038.safetensors", "model.layers.58.input_layernorm.weight": "model-00026-of-00038.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00026-of-00038.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00026-of-00038.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00026-of-00038.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00026-of-00038.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00026-of-00038.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00027-of-00038.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00027-of-00038.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00027-of-00038.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00027-of-00038.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00027-of-00038.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00027-of-00038.safetensors", "model.layers.59.input_layernorm.weight": "model-00027-of-00038.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00027-of-00038.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00027-of-00038.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00027-of-00038.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00027-of-00038.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00027-of-00038.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00027-of-00038.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00027-of-00038.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00027-of-00038.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00027-of-00038.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00027-of-00038.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00027-of-00038.safetensors", "model.layers.6.input_layernorm.weight": "model-00027-of-00038.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00027-of-00038.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00027-of-00038.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00027-of-00038.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00027-of-00038.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00027-of-00038.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00027-of-00038.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00027-of-00038.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00027-of-00038.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00027-of-00038.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00027-of-00038.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00027-of-00038.safetensors", "model.layers.60.input_layernorm.weight": "model-00027-of-00038.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00028-of-00038.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00028-of-00038.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00028-of-00038.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00028-of-00038.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00028-of-00038.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00028-of-00038.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00028-of-00038.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00028-of-00038.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00028-of-00038.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00028-of-00038.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00028-of-00038.safetensors", "model.layers.61.input_layernorm.weight": "model-00028-of-00038.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00028-of-00038.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00028-of-00038.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00028-of-00038.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00028-of-00038.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00028-of-00038.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00028-of-00038.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00028-of-00038.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00028-of-00038.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00028-of-00038.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00028-of-00038.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00028-of-00038.safetensors", "model.layers.62.input_layernorm.weight": "model-00028-of-00038.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00028-of-00038.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00029-of-00038.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00029-of-00038.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00029-of-00038.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00029-of-00038.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00029-of-00038.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00029-of-00038.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00029-of-00038.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00029-of-00038.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00029-of-00038.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00029-of-00038.safetensors", "model.layers.63.input_layernorm.weight": "model-00029-of-00038.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00029-of-00038.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00029-of-00038.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00029-of-00038.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00029-of-00038.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00029-of-00038.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00029-of-00038.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00029-of-00038.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00029-of-00038.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00029-of-00038.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00029-of-00038.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00029-of-00038.safetensors", "model.layers.64.input_layernorm.weight": "model-00029-of-00038.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00029-of-00038.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00029-of-00038.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00030-of-00038.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00030-of-00038.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00030-of-00038.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00030-of-00038.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00030-of-00038.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00030-of-00038.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00030-of-00038.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00030-of-00038.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00030-of-00038.safetensors", "model.layers.65.input_layernorm.weight": "model-00030-of-00038.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00030-of-00038.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00030-of-00038.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00030-of-00038.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00030-of-00038.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00030-of-00038.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00030-of-00038.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00030-of-00038.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00030-of-00038.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00030-of-00038.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00030-of-00038.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00030-of-00038.safetensors", "model.layers.66.input_layernorm.weight": "model-00030-of-00038.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00030-of-00038.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00030-of-00038.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00030-of-00038.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00030-of-00038.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00030-of-00038.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00031-of-00038.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00031-of-00038.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00031-of-00038.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00031-of-00038.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00031-of-00038.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00031-of-00038.safetensors", "model.layers.67.input_layernorm.weight": "model-00031-of-00038.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00031-of-00038.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00031-of-00038.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00031-of-00038.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00031-of-00038.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00031-of-00038.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00031-of-00038.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00031-of-00038.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00031-of-00038.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00031-of-00038.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00031-of-00038.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00031-of-00038.safetensors", "model.layers.68.input_layernorm.weight": "model-00031-of-00038.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00031-of-00038.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00031-of-00038.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00031-of-00038.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00031-of-00038.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00031-of-00038.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00031-of-00038.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00031-of-00038.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00031-of-00038.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00031-of-00038.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00031-of-00038.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00031-of-00038.safetensors", "model.layers.69.input_layernorm.weight": "model-00031-of-00038.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00032-of-00038.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00032-of-00038.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00032-of-00038.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00032-of-00038.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00032-of-00038.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00032-of-00038.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00032-of-00038.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00032-of-00038.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00032-of-00038.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00032-of-00038.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00032-of-00038.safetensors", "model.layers.7.input_layernorm.weight": "model-00032-of-00038.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00032-of-00038.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00032-of-00038.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00032-of-00038.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00032-of-00038.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00032-of-00038.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00032-of-00038.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00032-of-00038.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00032-of-00038.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00032-of-00038.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00032-of-00038.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00032-of-00038.safetensors", "model.layers.70.input_layernorm.weight": "model-00032-of-00038.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00032-of-00038.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00033-of-00038.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00033-of-00038.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00033-of-00038.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00033-of-00038.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00033-of-00038.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00033-of-00038.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00033-of-00038.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00033-of-00038.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00033-of-00038.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00033-of-00038.safetensors", "model.layers.71.input_layernorm.weight": "model-00033-of-00038.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00033-of-00038.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00033-of-00038.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00033-of-00038.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00033-of-00038.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00033-of-00038.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00033-of-00038.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00033-of-00038.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00033-of-00038.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00033-of-00038.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00033-of-00038.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00033-of-00038.safetensors", "model.layers.72.input_layernorm.weight": "model-00033-of-00038.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00033-of-00038.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00033-of-00038.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00034-of-00038.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00034-of-00038.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00034-of-00038.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00034-of-00038.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00034-of-00038.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00034-of-00038.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00034-of-00038.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00034-of-00038.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00034-of-00038.safetensors", "model.layers.73.input_layernorm.weight": "model-00034-of-00038.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00034-of-00038.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00034-of-00038.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00034-of-00038.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00034-of-00038.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00034-of-00038.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00034-of-00038.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00034-of-00038.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00034-of-00038.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00034-of-00038.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00034-of-00038.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00034-of-00038.safetensors", "model.layers.74.input_layernorm.weight": "model-00034-of-00038.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00034-of-00038.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00034-of-00038.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00034-of-00038.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00034-of-00038.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00034-of-00038.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00035-of-00038.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00035-of-00038.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00035-of-00038.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00035-of-00038.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00035-of-00038.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00035-of-00038.safetensors", "model.layers.75.input_layernorm.weight": "model-00035-of-00038.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00035-of-00038.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00035-of-00038.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00035-of-00038.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00035-of-00038.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00035-of-00038.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00035-of-00038.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00035-of-00038.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00035-of-00038.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00035-of-00038.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00035-of-00038.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00035-of-00038.safetensors", "model.layers.76.input_layernorm.weight": "model-00035-of-00038.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00035-of-00038.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00035-of-00038.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00035-of-00038.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00035-of-00038.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00035-of-00038.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00035-of-00038.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00035-of-00038.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00035-of-00038.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00035-of-00038.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00035-of-00038.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00035-of-00038.safetensors", "model.layers.77.input_layernorm.weight": "model-00035-of-00038.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00036-of-00038.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00036-of-00038.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00036-of-00038.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00036-of-00038.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00036-of-00038.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00036-of-00038.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00036-of-00038.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00036-of-00038.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00036-of-00038.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00036-of-00038.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00036-of-00038.safetensors", "model.layers.78.input_layernorm.weight": "model-00036-of-00038.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00036-of-00038.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00036-of-00038.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00036-of-00038.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00036-of-00038.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00036-of-00038.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00036-of-00038.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00036-of-00038.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00036-of-00038.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00036-of-00038.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00036-of-00038.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00036-of-00038.safetensors", "model.layers.79.input_layernorm.weight": "model-00036-of-00038.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00036-of-00038.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00037-of-00038.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00037-of-00038.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00037-of-00038.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00037-of-00038.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00037-of-00038.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00037-of-00038.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00037-of-00038.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00037-of-00038.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00037-of-00038.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.input_layernorm.weight": "model-00037-of-00038.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00037-of-00038.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00037-of-00038.safetensors", "model.layers.9.input_layernorm.weight": "model-00037-of-00038.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00037-of-00038.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00037-of-00038.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00038-of-00038.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00038-of-00038.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00038-of-00038.safetensors", "model.norm.weight": "model-00038-of-00038.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}