Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +303 -3
- config.json +30 -0
- generation_config.json +8 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +405 -0
- tokenizer.json +3 -0
- tokenizer_config.json +77 -0
.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 |
-
|
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> & <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 |
+
}
|