SeongBeomLEE commited on
Commit
4bc96c6
·
verified ·
1 Parent(s): f7bf127

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,303 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ pipeline_tag: text-generation
5
+ base_model:
6
+ - Qwen/Qwen3-4B-Base
7
+ tags:
8
+ - konanllm
9
+ language:
10
+ - ko
11
+ - en
12
+ ---
13
+ # Konan-LLM-OND
14
+
15
+ ## **Overview**
16
+
17
+ **Konan-LLM-OND**, a large language model from Konan Technology Inc., is based on [Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base). It has been specifically optimized for the Korean language through vocabulary expansion, continual pre-training, and instruction tuning to enhance performance and efficiency.
18
+ * **Languages**: Primarily Korean, with support for English.
19
+ * **Key Features:**
20
+ * **Expanded Korean Vocabulary:** The model's vocabulary has been expanded with additional Korean tokens to improve tokenization efficiency. As a result, Konan-LLM-OND is approximately 30% more token-efficient with Korean input than Qwen3, leading to greater cost-effectiveness and processing speed.
21
+ * **Continual Pre-training**: The model underwent continual pre-training on a large-scale Korean corpus using an expanded vocabulary. This process enhanced its fundamental understanding and text generation capabilities in Korean.
22
+ * **Supervised Fine-Tuning (SFT):** The model was fine-tuned on a high-quality Korean instruction dataset to improve its ability to understand and execute a wide variety of real-world tasks.
23
+
24
+ ## Benchmark Results
25
+
26
+ #### **Model Performance (< 5B)**
27
+
28
+ <table border="1" style="border-collapse: collapse; width: 100%;">
29
+ <thead>
30
+ <tr>
31
+ <th rowspan="2" style="text-align: center; padding: 8px;">Model</th>
32
+ <th rowspan="2" style="text-align: center; padding: 8px;">Model size</th>
33
+ <th colspan="3" style="text-align: center; padding: 8px;">Korean</th>
34
+ <th colspan="3" style="text-align: center; padding: 8px;">English</th>
35
+ </tr>
36
+ <tr>
37
+ <th style="text-align: center; padding: 8px;">KMMLU</th>
38
+ <th style="text-align: center; padding: 8px;">HRM8K</th>
39
+ <th style="text-align: center; padding: 8px;">Ko-IFEval</th>
40
+ <th style="text-align: center; padding: 8px;">MMLU</th>
41
+ <th style="text-align: center; padding: 8px;">GSM8K</th>
42
+ <th style="text-align: center; padding: 8px;">IFEval</th>
43
+ </tr>
44
+ </thead>
45
+ <tbody>
46
+ <tr>
47
+ <td style="padding: 8px;"><strong>Konan-LLM-OND</strong></td>
48
+ <td style="text-align: center; padding: 8px;">4.0B</td>
49
+ <td style="text-align: center; padding: 8px;"><strong>50.6<strong></td>
50
+ <td style="text-align: center; padding: 8px;"><strong>46.4<strong></td>
51
+ <td style="text-align: center; padding: 8px;">68.4</td>
52
+ <td style="text-align: center; padding: 8px;"><strong>68.8<strong></td>
53
+ <td style="text-align: center; padding: 8px;"><strong>86.8<strong></td>
54
+ <td style="text-align: center; padding: 8px;">73.3</td>
55
+ </tr>
56
+ <tr>
57
+ <td style="padding: 8px;"><strong>EXAONE-3.5-2.4B-Instruct</strong></td>
58
+ <td style="text-align: center; padding: 8px;">2.4B</td>
59
+ <td style="text-align: center; padding: 8px;">44.2</td>
60
+ <td style="text-align: center; padding: 8px;">31.8</td>
61
+ <td style="text-align: center; padding: 8px;">60.5</td>
62
+ <td style="text-align: center; padding: 8px;">59.1</td>
63
+ <td style="text-align: center; padding: 8px;">81.5</td>
64
+ <td style="text-align: center; padding: 8px;">77.7</td>
65
+ </tr>
66
+ <tr>
67
+ <td style="padding: 8px;"><strong>kanana-1.5-2.1b-instruct-2505</strong></td>
68
+ <td style="text-align: center; padding: 8px;">2.1B</td>
69
+ <td style="text-align: center; padding: 8px;">32.7</td>
70
+ <td style="text-align: center; padding: 8px;">27.2</td>
71
+ <td style="text-align: center; padding: 8px;">56.0</td>
72
+ <td style="text-align: center; padding: 8px;">52.9</td>
73
+ <td style="text-align: center; padding: 8px;">68.8</td>
74
+ <td style="text-align: center; padding: 8px;">64.6</td>
75
+ </tr>
76
+ <tr>
77
+ <td style="padding: 8px;"><strong>Midm-2.0-Mini-Instruct</strong></td>
78
+ <td style="text-align: center; padding: 8px;">2.3B</td>
79
+ <td style="text-align: center; padding: 8px;">42.4</td>
80
+ <td style="text-align: center; padding: 8px;">36.2</td>
81
+ <td style="text-align: center; padding: 8px;">66.8</td>
82
+ <td style="text-align: center; padding: 8px;">57.4</td>
83
+ <td style="text-align: center; padding: 8px;">74.8</td>
84
+ <td style="text-align: center; padding: 8px;">68.3</td>
85
+ </tr>
86
+ <tr>
87
+ <td style="padding: 8px;"><strong>Qwen3-4B(w/o reasoning)</strong></td>
88
+ <td style="text-align: center; padding: 8px;">4.0B</td>
89
+ <td style="text-align: center; padding: 8px;">0.0(*)</td>
90
+ <td style="text-align: center; padding: 8px;">37.5</td>
91
+ <td style="text-align: center; padding: 8px;">68.4</td>
92
+ <td style="text-align: center; padding: 8px;">29.4(*)</td>
93
+ <td style="text-align: center; padding: 8px;">83.9</td>
94
+ <td style="text-align: center; padding: 8px;"><strong>80.0<strong></td>
95
+ </tr>
96
+ <tr>
97
+ <td style="padding: 8px;"><strong>gemma-3-4b-it</strong></td>
98
+ <td style="text-align: center; padding: 8px;">4.3B</td>
99
+ <td style="text-align: center; padding: 8px;">38.7</td>
100
+ <td style="text-align: center; padding: 8px;">32.7</td>
101
+ <td style="text-align: center; padding: 8px;"><strong>69.2<strong></td>
102
+ <td style="text-align: center; padding: 8px;">59.1</td>
103
+ <td style="text-align: center; padding: 8px;">82.2</td>
104
+ <td style="text-align: center; padding: 8px;">78.3</td>
105
+ </tr>
106
+ </tbody>
107
+ </table>
108
+
109
+ #### **Model Performance (≥ 7B)**
110
+
111
+ <table border="1" style="border-collapse: collapse; width: 100%;">
112
+ <thead>
113
+ <tr>
114
+ <th rowspan="2" style="text-align: center; padding: 8px;">Model</th>
115
+ <th rowspan="2" style="text-align: center; padding: 8px;">Model size</th>
116
+ <th colspan="3" style="text-align: center; padding: 8px;">Korean</th>
117
+ <th colspan="3" style="text-align: center; padding: 8px;">English</th>
118
+ </tr>
119
+ <tr>
120
+ <th style="text-align: center; padding: 8px;">KMMLU</th>
121
+ <th style="text-align: center; padding: 8px;">HRM8K</th>
122
+ <th style="text-align: center; padding: 8px;">Ko-IFEval</th>
123
+ <th style="text-align: center; padding: 8px;">MMLU</th>
124
+ <th style="text-align: center; padding: 8px;">GSM8K</th>
125
+ <th style="text-align: center; padding: 8px;">IFEval</th>
126
+ </tr>
127
+ </thead>
128
+ <tbody>
129
+ <tr>
130
+ <td style="padding: 8px;"><strong>Konan-LLM-OND</strong></td>
131
+ <td style="text-align: center; padding: 8px;">4.0B</td>
132
+ <td style="text-align: center; padding: 8px;">50.6</td>
133
+ <td style="text-align: center; padding: 8px;"><strong>46.4</strong></td>
134
+ <td style="text-align: center; padding: 8px;">68.4</td>
135
+ <td style="text-align: center; padding: 8px;">68.8</td>
136
+ <td style="text-align: center; padding: 8px;">86.8</td>
137
+ <td style="text-align: center; padding: 8px;">73.3</td>
138
+ </tr>
139
+ <tr>
140
+ <td style="padding: 8px;"><strong>A.X-4.0-Light</strong></td>
141
+ <td style="text-align: center; padding: 8px;">7.2B</td>
142
+ <td style="text-align: center; padding: 8px;"><strong>55.3</strong></td>
143
+ <td style="text-align: center; padding: 8px;">44.6</td>
144
+ <td style="text-align: center; padding: 8px;">71.5</td>
145
+ <td style="text-align: center; padding: 8px;"><strong>70.6</strong></td>
146
+ <td style="text-align: center; padding: 8px;">87.3</td>
147
+ <td style="text-align: center; padding: 8px;">81.3</td>
148
+ </tr>
149
+ <tr>
150
+ <td style="padding: 8px;"><strong>EXAONE-3.5-7.8B-Instruct</strong></td>
151
+ <td style="text-align: center; padding: 8px;">7.8B</td>
152
+ <td style="text-align: center; padding: 8px;">48.0</td>
153
+ <td style="text-align: center; padding: 8px;">39.3</td>
154
+ <td style="text-align: center; padding: 8px;">66.8</td>
155
+ <td style="text-align: center; padding: 8px;">66.8</td>
156
+ <td style="text-align: center; padding: 8px;"><strong>91.4</strong></td>
157
+ <td style="text-align: center; padding: 8px;">79.9</td>
158
+ </tr>
159
+ <tr>
160
+ <td style="padding: 8px;"><strong>kanana-1.5-8b-instruct-2505</strong></td>
161
+ <td style="text-align: center; padding: 8px;">8.0B</td>
162
+ <td style="text-align: center; padding: 8px;">40.4</td>
163
+ <td style="text-align: center; padding: 8px;">35.5</td>
164
+ <td style="text-align: center; padding: 8px;">71.1</td>
165
+ <td style="text-align: center; padding: 8px;">63.1</td>
166
+ <td style="text-align: center; padding: 8px;">79.3</td>
167
+ <td style="text-align: center; padding: 8px;">76.8</td>
168
+ </tr>
169
+ <tr>
170
+ <td style="padding: 8px;"><strong>Midm-2.0-Base-Instruct</strong></td>
171
+ <td style="text-align: center; padding: 8px;">11.5B</td>
172
+ <td style="text-align: center; padding: 8px;">54.2</td>
173
+ <td style="text-align: center; padding: 8px;">46.0</td>
174
+ <td style="text-align: center; padding: 8px;"><strong>75.0</strong></td>
175
+ <td style="text-align: center; padding: 8px;">70.2</td>
176
+ <td style="text-align: center; padding: 8px;">88.9</td>
177
+ <td style="text-align: center; padding: 8px;">79.7</td>
178
+ </tr>
179
+ <tr>
180
+ <td style="padding: 8px;"><strong>Qwen3-8B(w/o reasoning)</strong></td>
181
+ <td style="text-align: center; padding: 8px;">8.1B</td>
182
+ <td style="text-align: center; padding: 8px;">0.0(*)</td>
183
+ <td style="text-align: center; padding: 8px;">40.0</td>
184
+ <td style="text-align: center; padding: 8px;">70.9</td>
185
+ <td style="text-align: center; padding: 8px;">7.4(*)</td>
186
+ <td style="text-align: center; padding: 8px;">84.0</td>
187
+ <td style="text-align: center; padding: 8px;"><strong>82.8</strong></td>
188
+ </tr>
189
+ </tbody>
190
+ </table>
191
+
192
+ Note:
193
+ * The highest scores are shown in bold.
194
+ * (*) Qwen3 models often failed to follow the required answer format in the few-shot setting. As a result, the MMLU and KMMLU scores are markedly lower than expected and should be considered unreliable.
195
+
196
+ ## **Benchmark Setup**
197
+
198
+ All benchmarks were executed using the following standardized environment.
199
+
200
+ * **Evaluation Framework**: `lm-evaluation-harness v0.4.9`
201
+ * **Runtime & Hardware**: All models were served with `vLLM v0.9.1` on a single NVIDIA GPU.
202
+ * **Inference Mode**: For every benchmark, we invoked the `chat_completions` API, and scores were computed solely from the generated responses.
203
+
204
+ #### **Metric Adjustments**
205
+
206
+ * MMLU was evaluated following the KMMLU protocol.
207
+ * Ko-IFEval was evaluated using the original IFEval protocol, with the dataset sourced from [allganize/IFEval-Ko](https://huggingface.co/datasets/allganize/IFEval-Ko).
208
+
209
+ #### **Evaluation Protocol**
210
+
211
+ <table>
212
+ <thead>
213
+ <tr>
214
+ <th>Benchmark</th>
215
+ <th>Scoring Method</th>
216
+ <th>Few-shot</th>
217
+ </tr>
218
+ </thead>
219
+ <tbody>
220
+ <tr>
221
+ <td><strong>KMMLU</strong></td>
222
+ <td><code>exact_match</code></td>
223
+ <td>5-shot</td>
224
+ </tr>
225
+ <tr>
226
+ <td><strong>HRM8K</strong></td>
227
+ <td>mean of <code>hrm8k_gsm8k</code>, <code>hrm8k_ksm</code>, <code>hrm8k_math</code>, <code>hrm8k_mmmlu</code>, <code>hrm8k_omni_math</code></td>
228
+ <td>5-shot</td>
229
+ </tr>
230
+ <tr>
231
+ <td><strong>Ko-IFEval</strong></td>
232
+ <td>mean of <code>prompt_level_strict_acc</code>, <code>inst_level_strict_acc</code>, <code>prompt_level_loose_acc</code>, <code>inst_level_loose_acc</code></td>
233
+ <td>0-shot</td>
234
+ </tr>
235
+ <tr>
236
+ <td><strong>MMLU</strong></td>
237
+ <td><code>exact_match</code></td>
238
+ <td>5-shot</td>
239
+ </tr>
240
+ <tr>
241
+ <td><strong>GSM8K</strong></td>
242
+ <td><code>exact_match</code> &amp; <code>flexible-extract</code></td>
243
+ <td>5-shot</td>
244
+ </tr>
245
+ <tr>
246
+ <td><strong>IFEval</strong></td>
247
+ <td>mean of <code>prompt_level_strict_acc</code>, <code>inst_level_strict_acc</code>, <code>prompt_level_loose_acc</code>, <code>inst_level_loose_acc</code></td>
248
+ <td>0-shot</td>
249
+ </tr>
250
+ </tbody>
251
+ </table>
252
+
253
+ ## Quickstart
254
+
255
+ **Konan-LLM-OND** is supported in `transformers v4.52.0` and later.
256
+ ```bash
257
+ pip install transformers>=4.52.0
258
+ ```
259
+
260
+ The code example below shows you how to get the model to generate content based on given inputs.
261
+ ```python
262
+ import torch
263
+ from transformers import AutoTokenizer, AutoModelForCausalLM
264
+
265
+ model_name = "konantech/Konan-LLM-OND"
266
+ model = AutoModelForCausalLM.from_pretrained(
267
+ model_name,
268
+ torch_dtype=torch.bfloat16,
269
+ device_map="auto",
270
+ )
271
+ model.eval()
272
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
273
+
274
+ messages = [
275
+ {"role": "system", "content": "You are a helpful assistant."},
276
+ {"role": "user", "content": "대한민국 수도는?"}
277
+ ]
278
+
279
+
280
+ input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
281
+
282
+ with torch.no_grad():
283
+ output = model.generate(
284
+ input_ids,
285
+ max_new_tokens=64,
286
+ do_sample=False,
287
+ )
288
+
289
+ len_input_prompt = len(input_ids[0])
290
+ response = tokenizer.decode(output[0][len_input_prompt:], skip_special_tokens=True)
291
+ print(response)
292
+ # 대한민국 수도는 서울입니다.
293
+ ```
294
+
295
+ ## Citation
296
+ ```
297
+ @misc{Konan-LLM-OND-2025,
298
+ author = {Konan Technology Inc.},
299
+ title = {Konan-LLM-OND},
300
+ year = {2025},
301
+ url = {https://huggingface.co/konantech/Konan-LLM-OND}
302
+ }
303
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 172728,
8
+ "eos_token_id": 172730,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 36,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 36,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.52.0",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 172800
30
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 172728,
3
+ "eos_token_id": [
4
+ 172730,
5
+ 172728
6
+ ],
7
+ "transformers_version": "4.52.0"
8
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a53c5afba674a00b7e152ebcf8ad778ac55bfbcd42ae065570fb783ddb1d8041
3
+ size 4974424112
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d177f351d3a2e1fd041c28b94274e0fa84a0a5e811cebd4217ecaa0db91e5bf
3
+ size 3177381584
model.safetensors.index.json ADDED
@@ -0,0 +1,405 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8151759872
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
291
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
293
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
338
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
344
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
349
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
351
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
353
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
354
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
356
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
357
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
358
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
360
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
361
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
362
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
364
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
365
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
366
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.norm.weight": "model-00002-of-00002.safetensors"
404
+ }
405
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31013d56c27df6a860275f50df7013e9ba8fabc62304da23841a003183c3420
3
+ size 13252355
tokenizer_config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "172728": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "172729": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "172730": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "172731": {
30
+ "content": "<tool_call>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "172732": {
38
+ "content": "</tool_call>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "172733": {
46
+ "content": "<tool_response>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "172734": {
54
+ "content": "</tool_response>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "<|im_start|>",
64
+ "<|im_end|>"
65
+ ],
66
+ "bos_token": null,
67
+ "chat_template": "{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}\n {%- elif message['role'] == 'user' -%}\n {{ '<|im_start|>user\n' + message['content'] + '<|im_end|>\n' }}\n {%- elif message['role'] == 'assistant' -%}\n {{ '<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{ '<|im_start|>assistant\n' }}\n{%- endif -%}",
68
+ "clean_up_tokenization_spaces": false,
69
+ "eos_token": "<|im_end|>",
70
+ "errors": "replace",
71
+ "extra_special_tokens": {},
72
+ "model_max_length": 131072,
73
+ "pad_token": "<|endoftext|>",
74
+ "split_special_tokens": false,
75
+ "tokenizer_class": "Qwen2Tokenizer",
76
+ "unk_token": null
77
+ }