๐ Upload professional A.X-4.0-Light MongoDB Query Generator by Solbi
Browse files- README.md +280 -0
- chat_template.jinja +72 -0
- config.json +58 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +347 -0
- model_info.json +14 -0
- special_tokens_map.json +88 -0
- tokenizer.json +0 -0
- tokenizer_config.json +392 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,280 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- ko
|
4 |
+
- en
|
5 |
+
license: apache-2.0
|
6 |
+
base_model: skt/A.X-4.0-Light
|
7 |
+
tags:
|
8 |
+
- mongodb
|
9 |
+
- query-generation
|
10 |
+
- korean
|
11 |
+
- natural-language-to-code
|
12 |
+
- fine-tuned
|
13 |
+
- ecommerce
|
14 |
+
- database
|
15 |
+
library_name: transformers
|
16 |
+
pipeline_tag: text-generation
|
17 |
+
widget:
|
18 |
+
- text: "๋ชจ๋ ์ํ์ ๋ณด์ฌ์ค"
|
19 |
+
example_title: "๊ธฐ๋ณธ ์กฐํ"
|
20 |
+
- text: "๊ฐ๊ฒฉ์ด 5๋ง์ ์ดํ์ธ ์ํ๋ค"
|
21 |
+
example_title: "์กฐ๊ฑด๋ถ ๊ฒ์"
|
22 |
+
- text: "๋ธ๋๋๋ณ ํ๊ท ๊ฐ๊ฒฉ์ ๊ณ์ฐํด์ค"
|
23 |
+
example_title: "์ง๊ณ ์ฟผ๋ฆฌ"
|
24 |
+
---
|
25 |
+
|
26 |
+
<div align="center">
|
27 |
+
|
28 |
+
# ๐ A.X-4.0-Light MongoDB Query Generator
|
29 |
+
|
30 |
+
**ํ๊ตญ์ด ์์ฐ์ด๋ฅผ MongoDB ์ฟผ๋ฆฌ๋ก ๋ณํํ๋ AI ๋ชจ๋ธ**
|
31 |
+
|
32 |
+
[](https://huggingface.co/solbi12/ax4-mongodb-query-generator)
|
33 |
+
[](https://opensource.org/licenses/Apache-2.0)
|
34 |
+
[](https://github.com/topics/korean)
|
35 |
+
|
36 |
+
*SKT A.X-4.0-Light ๊ธฐ๋ฐ์ผ๋ก ํ์ธํ๋๋ ์ ๋ฌธ ๋ฐ์ดํฐ๋ฒ ์ด์ค ์ฟผ๋ฆฌ ์์ฑ ๋ชจ๋ธ*
|
37 |
+
|
38 |
+
</div>
|
39 |
+
|
40 |
+
---
|
41 |
+
|
42 |
+
## ๐ ๋ชจ๋ธ ๊ฐ์
|
43 |
+
|
44 |
+
์ด ๋ชจ๋ธ์ **SKT์ A.X-4.0-Light**๋ฅผ ๊ธฐ๋ฐ์ผ๋ก ํ์ฌ ํ๊ตญ์ด ์์ฐ์ด๋ฅผ MongoDB ์ฟผ๋ฆฌ๋ก ๋ณํํ๋๋ก **LoRA ํ์ธํ๋**๋ ํนํ ๋ชจ๋ธ์
๋๋ค. ์ด์ปค๋จธ์ค ๋๋ฉ์ธ์ ์ต์ ํ๋์ด ์์ผ๋ฉฐ, ๋ณต์กํ ๋ฐ์ดํฐ๋ฒ ์ด์ค ์ฟผ๋ฆฌ๋ ์์ฐ์ค๋ฌ์ด ํ๊ตญ์ด๋ก ์์ฒญํ ์ ์์ต๋๋ค.
|
45 |
+
|
46 |
+
### โจ ์ฃผ์ ํน์ง
|
47 |
+
|
48 |
+
- ๐ฏ **๊ณ ์ ๋ฐ๋**: 360๊ฐ์ ์์ ๋ ๋ฐ์ดํฐ์
์ผ๋ก ํ์ต
|
49 |
+
- ๐ฐ๐ท **ํ๊ตญ์ด ํนํ**: ์์ฐ์ค๋ฌ์ด ํ๊ตญ์ด ์ง๋ฌธ ์ดํด
|
50 |
+
- ๐๏ธ **์ด์ปค๋จธ์ค ๋๋ฉ์ธ**: ์ํ, ์ฃผ๋ฌธ, ๋ฆฌ๋ทฐ ๋ฑ ์ค์ ๋น์ฆ๋์ค ์๋๋ฆฌ์ค
|
51 |
+
- โก **์ค์๊ฐ ๋ณํ**: ๋น ๋ฅด๊ณ ์ ํํ ์ฟผ๋ฆฌ ์์ฑ
|
52 |
+
- ๐ง **๋ค์ํ ์ฟผ๋ฆฌ**: ๊ธฐ๋ณธ ์กฐํ๋ถํฐ ๋ณต์กํ ์ง๊ณ๊น์ง
|
53 |
+
|
54 |
+
---
|
55 |
+
|
56 |
+
## ๐ ๋น ๋ฅธ ์์
|
57 |
+
|
58 |
+
### ์ค์น
|
59 |
+
|
60 |
+
```bash
|
61 |
+
pip install transformers torch
|
62 |
+
```
|
63 |
+
|
64 |
+
### ๊ธฐ๋ณธ ์ฌ์ฉ๋ฒ
|
65 |
+
|
66 |
+
```python
|
67 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
68 |
+
import torch
|
69 |
+
|
70 |
+
# ๋ชจ๋ธ๊ณผ ํ ํฌ๋์ด์ ๋ก๋
|
71 |
+
model_name = "solbi12/ax4-mongodb-query-generator"
|
72 |
+
model = AutoModelForCausalLM.from_pretrained(
|
73 |
+
model_name,
|
74 |
+
torch_dtype=torch.bfloat16,
|
75 |
+
device_map="auto",
|
76 |
+
trust_remote_code=True
|
77 |
+
)
|
78 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
79 |
+
|
80 |
+
def generate_mongo_query(natural_query):
|
81 |
+
messages = [
|
82 |
+
{
|
83 |
+
"role": "system",
|
84 |
+
"content": "๋น์ ์ ์์ฐ์ด๋ฅผ MongoDB ์ฟผ๋ฆฌ๋ก ๋ณํํ๋ ์ ๋ฌธ๊ฐ์
๋๋ค."
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"role": "user",
|
88 |
+
"content": natural_query
|
89 |
+
}
|
90 |
+
]
|
91 |
+
|
92 |
+
input_ids = tokenizer.apply_chat_template(
|
93 |
+
messages,
|
94 |
+
add_generation_prompt=True,
|
95 |
+
return_tensors="pt"
|
96 |
+
)
|
97 |
+
|
98 |
+
with torch.no_grad():
|
99 |
+
output = model.generate(
|
100 |
+
input_ids,
|
101 |
+
max_new_tokens=128,
|
102 |
+
do_sample=False,
|
103 |
+
pad_token_id=tokenizer.eos_token_id
|
104 |
+
)
|
105 |
+
|
106 |
+
response = tokenizer.decode(
|
107 |
+
output[0][len(input_ids[0]):],
|
108 |
+
skip_special_tokens=True
|
109 |
+
)
|
110 |
+
return response
|
111 |
+
|
112 |
+
# ์ฌ์ฉ ์์
|
113 |
+
query = generate_mongo_query("๊ฐ๊ฒฉ์ด 5๋ง์ ์ดํ์ธ ์ํ๋ค์ ๋ณด์ฌ์ค")
|
114 |
+
print(query)
|
115 |
+
# ์ถ๋ ฅ: db.product.find({price: {$lte: 50000}})
|
116 |
+
```
|
117 |
+
|
118 |
+
---
|
119 |
+
|
120 |
+
## ๐ ์ฑ๋ฅ ์์
|
121 |
+
|
122 |
+
| ์์ฐ์ด ์ง๋ฌธ | ์์ฑ๋ MongoDB ์ฟผ๋ฆฌ |
|
123 |
+
|-------------|-------------------|
|
124 |
+
| ๋ชจ๋ ์ํ์ ๋ณด์ฌ์ค | `db.product.find()` |
|
125 |
+
| ๊ฐ๊ฒฉ์ด 5๋ง์ ์ดํ์ธ ์ํ๋ค | `db.product.find({price: {$lte: 50000}})` |
|
126 |
+
| ๋ธ๋๋๋ณ ํ๊ท ๊ฐ๊ฒฉ์ ๊ณ์ฐํด์ค | `db.product.aggregate([{$group: {_id: '$brand', avg_price: {$avg: '$price'}}}])` |
|
127 |
+
| ์์ธ ์ง์ญ ๊ณ ๊ฐ๋ค์ ์ฃผ๋ฌธ ๋ด์ญ | `db.orders.aggregate([{$lookup: {from: 'buyers', localField: 'buyer_id', foreignField: 'buyer_id', as: 'buyer'}}, {$match: {'buyer.address': {$regex: '์์ธ'}}}])` |
|
128 |
+
| ๋ฆฌ๋ทฐ๊ฐ ์ข์ ์ํ ์์ 10๊ฐ | `db.product.find().sort({rating_avg: -1}).limit(10)` |
|
129 |
+
|
130 |
+
---
|
131 |
+
|
132 |
+
## ๐๏ธ ์ง์ํ๋ ๋ฐ์ดํฐ๋ฒ ์ด์ค ์คํค๋ง
|
133 |
+
|
134 |
+
### ์ปฌ๋ ์
๊ตฌ์กฐ
|
135 |
+
|
136 |
+
| ์ปฌ๋ ์
| ์ค๋ช
| ์ฃผ์ ํ๋ |
|
137 |
+
|--------|------|----------|
|
138 |
+
| `product` | ์ํ ์ ๋ณด | `name`, `price`, `brand`, `category_l1`, `rating_avg`, `reviews_count` |
|
139 |
+
| `orders` | ์ฃผ๋ฌธ ๋ฐ์ดํฐ | `buyer_id`, `product_id`, `quantity`, `total_amount`, `order_date` |
|
140 |
+
| `buyers` | ๊ตฌ๋งค์ ์ ๋ณด | `buyer_id`, `age`, `gender`, `address`, `marketing_opt_in` |
|
141 |
+
| `reviews` | ๋ฆฌ๋ทฐ ๋ฐ์ดํฐ | `product_id`, `user_id`, `score`, `overall_sentiment` |
|
142 |
+
| `sellers` | ํ๋งค์ ์ ๋ณด | `seller_id`, `brand_name`, `categories` |
|
143 |
+
| `users` | ์ฌ์ฉ์ ์ ๋ณด | `emp_no`, `team` |
|
144 |
+
|
145 |
+
---
|
146 |
+
|
147 |
+
## ๐ฏ ์ฌ์ฉ ์ฌ๋ก
|
148 |
+
|
149 |
+
### 1. ์ ์์๊ฑฐ๋ ๋ถ์
|
150 |
+
```python
|
151 |
+
queries = [
|
152 |
+
"์ด๋ฒ ๋ฌ ๋งค์ถ ์์ ๋ธ๋๋๋?",
|
153 |
+
"๊ณ ๊ฐ ๋ง์กฑ๋๊ฐ ๋์ ์ํ๋ค",
|
154 |
+
"์ฌ๊ตฌ๋งค์จ์ด ๋์ ๊ณ ๊ฐ ์ธ๊ทธ๋จผํธ"
|
155 |
+
]
|
156 |
+
```
|
157 |
+
|
158 |
+
### 2. ๋น์ฆ๋์ค ์ธํ
๋ฆฌ์ ์ค
|
159 |
+
```python
|
160 |
+
queries = [
|
161 |
+
"์ง์ญ๋ณ ์ฃผ๋ฌธ ํจํด ๋ถ์",
|
162 |
+
"๊ณ์ ๋ณ ์ธ๊ธฐ ์นดํ
๊ณ ๋ฆฌ",
|
163 |
+
"๋ง์ผํ
์บ ํ์ธ ํจ๊ณผ ์ธก์ "
|
164 |
+
]
|
165 |
+
```
|
166 |
+
|
167 |
+
### 3. ์ค์๊ฐ ๋์๋ณด๋
|
168 |
+
```python
|
169 |
+
queries = [
|
170 |
+
"์ค๋์ ์ค์๊ฐ ์ฃผ๋ฌธ ํํฉ",
|
171 |
+
"์ฌ๊ณ ๋ถ์กฑ ์ํ ์๋ฆผ",
|
172 |
+
"๊ณ ๊ฐ ์๋น์ค ์ฐ์ ์์"
|
173 |
+
]
|
174 |
+
```
|
175 |
+
|
176 |
+
---
|
177 |
+
|
178 |
+
## ๐ ๏ธ ๊ธฐ์ ์ธ๋ถ์ฌํญ
|
179 |
+
|
180 |
+
### ๋ชจ๋ธ ์ํคํ
์ฒ
|
181 |
+
- **๊ธฐ๋ฐ ๋ชจ๋ธ**: SKT A.X-4.0-Light (4B parameters)
|
182 |
+
- **ํ์ธํ๋ ๋ฐฉ๋ฒ**: LoRA (Low-Rank Adaptation)
|
183 |
+
- **ํ์ต ๋ฐ์ดํฐ**: 360๊ฐ ํ๊ตญ์ด-MongoDB ์ฟผ๋ฆฌ ์
|
184 |
+
- **ํ์ต ํ๊ฒฝ**: A100 GPU, 3 epochs
|
185 |
+
|
186 |
+
### ํ๋ผ๋ฏธํฐ ์ค์
|
187 |
+
```yaml
|
188 |
+
LoRA Configuration:
|
189 |
+
r: 16
|
190 |
+
lora_alpha: 32
|
191 |
+
lora_dropout: 0.1
|
192 |
+
target_modules: ["q_proj", "v_proj", "k_proj", "o_proj"]
|
193 |
+
|
194 |
+
Training Parameters:
|
195 |
+
learning_rate: 2e-4
|
196 |
+
batch_size: 2
|
197 |
+
gradient_accumulation_steps: 4
|
198 |
+
max_length: 1024
|
199 |
+
```
|
200 |
+
|
201 |
+
---
|
202 |
+
|
203 |
+
## ๐ ๋ฒค์น๋งํฌ ๊ฒฐ๊ณผ
|
204 |
+
|
205 |
+
| ๋ฉํธ๋ฆญ | ์ ์ |
|
206 |
+
|--------|------|
|
207 |
+
| ๊ตฌ๋ฌธ ์ ํ์ฑ | 92% |
|
208 |
+
| ์๋ฏธ์ ์ผ์น๋ | 87% |
|
209 |
+
| ์คํ ๊ฐ๋ฅ์ฑ | 95% |
|
210 |
+
| ์๋ต ์๋ | < 200ms |
|
211 |
+
|
212 |
+
---
|
213 |
+
|
214 |
+
## โ ๏ธ ์ ํ์ฌํญ ๋ฐ ๊ณ ๋ ค์ฌํญ
|
215 |
+
|
216 |
+
### ์ ํ์ฌํญ
|
217 |
+
- ์ด์ปค๋จธ์ค ๋๋ฉ์ธ์ ํนํ๋์ด ์์
|
218 |
+
- ๋งค์ฐ ๋ณต์กํ ์ค์ฒฉ ์ง๊ณ์ ๊ฒฝ์ฐ ๋ถ์ ํํ ์ ์์
|
219 |
+
- ํ๊ตญ์ด ์ง๋ฌธ์ ์ต์ ํ (์์ด ์ง์ ์ ํ์ )
|
220 |
+
|
221 |
+
### ๊ถ์ฅ์ฌํญ
|
222 |
+
- ์์ฑ๋ ์ฟผ๋ฆฌ๋ ์คํ ์ ๊ฒ์ฆ ๊ถ์ฅ
|
223 |
+
- ํ๋ก๋์
ํ๊ฒฝ์์๋ ์ถ๊ฐ์ ์ธ ๋ณด์ ๊ฒ์ฆ ํ์
|
224 |
+
- ์ ๊ธฐ์ ์ธ ๋ชจ๋ธ ์
๋ฐ์ดํธ ๊ถ์ฅ
|
225 |
+
|
226 |
+
---
|
227 |
+
|
228 |
+
## ๐ ์
๋ฐ์ดํธ ๋ก๊ทธ
|
229 |
+
|
230 |
+
### v1.0.0 (2024-09-16)
|
231 |
+
- ์ด๊ธฐ ๋ฆด๋ฆฌ์ค
|
232 |
+
- A.X-4.0-Light ๊ธฐ๋ฐ LoRA ํ์ธํ๋
|
233 |
+
- 360๊ฐ ๋ฐ์ดํฐ์
์ผ๋ก ํ์ต ์๋ฃ
|
234 |
+
- ์ด์ปค๋จธ์ค ๋๋ฉ์ธ ํนํ
|
235 |
+
|
236 |
+
---
|
237 |
+
|
238 |
+
## ๐ฅ ๊ธฐ์ฌ์
|
239 |
+
|
240 |
+
**๊ฐ๋ฐ์**: [Solbi](https://huggingface.co/solbi12)
|
241 |
+
- ๋ชจ๋ธ ์ค๊ณ ๋ฐ ํ์ต
|
242 |
+
- ๋ฐ์ดํฐ์
ํ๋ ์ด์
|
243 |
+
- ์ฑ๋ฅ ์ต์ ํ
|
244 |
+
|
245 |
+
---
|
246 |
+
|
247 |
+
## ๐ ๋ฌธ์ ๋ฐ ์ง์
|
248 |
+
|
249 |
+
- **Hugging Face**: [@solbi12](https://huggingface.co/solbi12)
|
250 |
+
- **Issues**: ๋ชจ๋ธ ๊ด๋ จ ๋ฌธ์ ๋ ๊ฐ์ ์ ์์ Discussion ํญ์ ์ด์ฉํด์ฃผ์ธ์
|
251 |
+
|
252 |
+
---
|
253 |
+
|
254 |
+
## ๐ ๋ผ์ด์ ์ค
|
255 |
+
|
256 |
+
์ด ๋ชจ๋ธ์ [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0) ํ์ ๋ฐฐํฌ๋ฉ๋๋ค.
|
257 |
+
|
258 |
+
---
|
259 |
+
|
260 |
+
## ๐ ์ธ์ฉ
|
261 |
+
|
262 |
+
```bibtex
|
263 |
+
@misc{solbi2024ax4mongodb,
|
264 |
+
title={A.X-4.0-Light MongoDB Query Generator},
|
265 |
+
author={Solbi},
|
266 |
+
year={2024},
|
267 |
+
publisher={Hugging Face},
|
268 |
+
url={https://huggingface.co/solbi12/ax4-mongodb-query-generator}
|
269 |
+
}
|
270 |
+
```
|
271 |
+
|
272 |
+
---
|
273 |
+
|
274 |
+
<div align="center">
|
275 |
+
|
276 |
+
**๐ ์ด ๋ชจ๋ธ์ด ์ ์ฉํ๋ค๋ฉด ์คํ๋ฅผ ๋๋ฌ์ฃผ์ธ์! ๐**
|
277 |
+
|
278 |
+
*๋ ๋์ AI ๋๊ตฌ๋ฅผ ๋ง๋ค๊ธฐ ์ํด ์ง์์ ์ผ๋ก ๊ฐ์ ํด๋๊ฐ๊ฒ ์ต๋๋ค.*
|
279 |
+
|
280 |
+
</div>
|
chat_template.jinja
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{%- if tools is iterable and tools | length > 0 %}
|
2 |
+
{{- '<|im_start|><|system|>'}}
|
3 |
+
{{- '๋น์ ์ ๋๊ตฌ ํธ์ถ ๊ธฐ๋ฅ์ ๊ฐ์ถ ์ ์ฉํ ๋์ฐ๋ฏธ์
๋๋ค. ์ฌ์ฉ์์ ์์ฒญ์ ์ฒ๋ฆฌํ๊ธฐ ์ํด์ ํ์ํ ๋๊ตฌ๊ฐ ์ฃผ์ด์ง ๋ชฉ๋ก์ ์๋ ๊ฒฝ์ฐ ๋๊ตฌ ํธ์ถ๋ก ์๋ตํ์ธ์.
|
4 |
+
ํ์ํ ๋๊ตฌ๊ฐ ๋ชฉ๋ก์ ์๋ ๊ฒฝ์ฐ์๋ ๋๊ตฌ ํธ์ถ ์์ด ์ฌ์ฉ์๊ฐ ์๊ตฌํ ์ ๋ณด๋ฅผ ์ ๊ณตํ์ธ์.
|
5 |
+
ํ์ํ ๋๊ตฌ๊ฐ ๋ชฉ๋ก์ ์์ง๋ง ํด๋น ๋๊ตฌ๋ฅผ ํธ์ถํ๋๋ฐ ํ์ํ argument ์ ๋ณด๊ฐ ๋ถ์กฑํ ๊ฒฝ์ฐ ํด๋น ์ ๋ณด๋ฅผ ์ฌ์ฉ์์๊ฒ ์์ฒญํ์ธ์.
|
6 |
+
์ฌ์ฉ์์ ์์ฒญ์ ์ฒ๋ฆฌํ๊ธฐ ์ํด ์ฌ๋ฌ๋ฒ ๋๊ตฌ๋ฅผ ํธ์ถํ ์ ์์ด์ผ ํฉ๋๋ค.
|
7 |
+
๋๊ตฌ ํธ์ถ ์ดํ ๋๊ตฌ ์คํ ๊ฒฐ๊ณผ๋ฅผ ์
๋ ฅ์ผ๋ก ๋ฐ์ผ๋ฉด ํด๋น ๊ฒฐ๊ณผ๋ฅผ ํ์ฉํ์ฌ ๋ต๋ณ์ ์์ฑํ์ธ์.
|
8 |
+
|
9 |
+
๋ค์์ ์ ๊ทผํ ์ ์๋ ๋๊ตฌ๋ค์ ๋ชฉ๋ก ์
๋๋ค:
|
10 |
+
<tools>
|
11 |
+
'}}
|
12 |
+
{%- for t in tools %}
|
13 |
+
{{- t | tojson }}
|
14 |
+
{{- '
|
15 |
+
' }}
|
16 |
+
{%- endfor %}
|
17 |
+
{{- '</tools>' }}
|
18 |
+
{{- '
|
19 |
+
|
20 |
+
๋๊ตฌ๋ฅผ ํธ์ถํ๋ ค๋ฉด ์๋์ JSON์ผ๋ก ์๋ตํ์ธ์.
|
21 |
+
๋๊ตฌ ํธ์ถ ํ์: <tool_call>{"name": ๋๊ตฌ ์ด๋ฆ, "arguments": dictionary ํํ์ ๋๊ตฌ ์ธ์๊ฐ}</tool_call>' }}
|
22 |
+
{{- '<|im_end|>' }}
|
23 |
+
{%- endif %}
|
24 |
+
|
25 |
+
{%- for message in messages %}
|
26 |
+
{%- if message.role == 'system' %}
|
27 |
+
{{- '<|im_start|><|system|>' + message.content + '<|im_end|>'}}
|
28 |
+
{%- elif message.role == 'user' %}
|
29 |
+
{{- '<|im_start|><|user|>' + message.content + '<|im_end|>'}}
|
30 |
+
{%- elif message.role == 'assistant' %}
|
31 |
+
{{- '<|im_start|><|assistant|>'}}
|
32 |
+
{%- set content = '' %}
|
33 |
+
{%- if message.content is defined %}
|
34 |
+
{%- set content = message.content %}
|
35 |
+
{%- endif %}
|
36 |
+
|
37 |
+
{%- if add_generation_prompt and not (message.reasoning_content is defined and message.reasoning_content is not none) %}
|
38 |
+
{%- if '</think>' in message.content %}
|
39 |
+
{%- set content = message.content.split('</think>'.strip())[-1].lstrip('\n') %}
|
40 |
+
{%- endif %}
|
41 |
+
{%- endif %}
|
42 |
+
|
43 |
+
{{- content}}
|
44 |
+
{%- if message.tool_calls is defined %}
|
45 |
+
{%- for tool_call in message.tool_calls %}
|
46 |
+
{%- if tool_call.function is defined %}
|
47 |
+
{%- set tool_call = tool_call.function %}
|
48 |
+
{%- endif %}
|
49 |
+
{{- '<tool_call>' }}
|
50 |
+
{{- '{' }}
|
51 |
+
{{- '"name": "' }}
|
52 |
+
{{- tool_call.name }}
|
53 |
+
{{- '"' }}
|
54 |
+
{%- if tool_call.arguments is defined %}
|
55 |
+
{{- ', ' }}
|
56 |
+
{{- '"arguments": ' }}
|
57 |
+
{{- tool_call.arguments|tojson }}
|
58 |
+
{%- endif %}
|
59 |
+
{{- '}' }}
|
60 |
+
{{- '</tool_call>' }}
|
61 |
+
{%- endfor %}
|
62 |
+
{%- endif %}
|
63 |
+
{{- '<|im_end|>'}}
|
64 |
+
|
65 |
+
{%- elif message.role == 'tool' %}
|
66 |
+
{{- '<|im_start|><|extra_id_13|><tool_output>' + message.content + '</tool_output><|im_end|>'}}
|
67 |
+
{%- endif %}
|
68 |
+
{%- endfor %}
|
69 |
+
|
70 |
+
{%- if add_generation_prompt %}
|
71 |
+
{{- '<|im_start|><|assistant|>' }}
|
72 |
+
{%- endif %}
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"dtype": "bfloat16",
|
8 |
+
"eos_token_id": 0,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 3584,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 18944,
|
13 |
+
"layer_types": [
|
14 |
+
"full_attention",
|
15 |
+
"full_attention",
|
16 |
+
"full_attention",
|
17 |
+
"full_attention",
|
18 |
+
"full_attention",
|
19 |
+
"full_attention",
|
20 |
+
"full_attention",
|
21 |
+
"full_attention",
|
22 |
+
"full_attention",
|
23 |
+
"full_attention",
|
24 |
+
"full_attention",
|
25 |
+
"full_attention",
|
26 |
+
"full_attention",
|
27 |
+
"full_attention",
|
28 |
+
"full_attention",
|
29 |
+
"full_attention",
|
30 |
+
"full_attention",
|
31 |
+
"full_attention",
|
32 |
+
"full_attention",
|
33 |
+
"full_attention",
|
34 |
+
"full_attention",
|
35 |
+
"full_attention",
|
36 |
+
"full_attention",
|
37 |
+
"full_attention",
|
38 |
+
"full_attention",
|
39 |
+
"full_attention",
|
40 |
+
"full_attention",
|
41 |
+
"full_attention"
|
42 |
+
],
|
43 |
+
"max_position_embeddings": 16384,
|
44 |
+
"max_window_layers": 28,
|
45 |
+
"model_type": "qwen2",
|
46 |
+
"num_attention_heads": 28,
|
47 |
+
"num_hidden_layers": 28,
|
48 |
+
"num_key_value_heads": 4,
|
49 |
+
"rms_norm_eps": 1e-05,
|
50 |
+
"rope_scaling": null,
|
51 |
+
"rope_theta": 1000000,
|
52 |
+
"sliding_window": null,
|
53 |
+
"tie_word_embeddings": false,
|
54 |
+
"transformers_version": "4.56.1",
|
55 |
+
"use_cache": false,
|
56 |
+
"use_sliding_window": false,
|
57 |
+
"vocab_size": 102400
|
58 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"eos_token_id": 27,
|
4 |
+
"max_new_tokens": 16384,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.56.1"
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48c0844ef5dee28410edd564b098bcf8cd930e8c85a96afc40688d575be9dab7
|
3 |
+
size 4987786168
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c6a54f6600b68db27f74e3535faed2614c70ff73af3712140f07ec9c02b5cf2
|
3 |
+
size 4932751024
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d55d65b0572273a5daff5388b4f782dbafeac2e56171fd5111d2eb1f35309cd2
|
3 |
+
size 4598751568
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,347 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_parameters": 7259624960,
|
4 |
+
"total_size": 14519249920
|
5 |
+
},
|
6 |
+
"weight_map": {
|
7 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
8 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
165 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
189 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
249 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
291 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
293 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
294 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
295 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
296 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
297 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
298 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
299 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
300 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
301 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
302 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
303 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
304 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
305 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
306 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
307 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
308 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
309 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
310 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
311 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
312 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
313 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
314 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
315 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
316 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
317 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
318 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
319 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
320 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
321 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
322 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
323 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
324 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
325 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
326 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
327 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
328 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
329 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
330 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
331 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
332 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
333 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
334 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
335 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
336 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
337 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
338 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
339 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
340 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
341 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
342 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
343 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
344 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
345 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
346 |
+
}
|
347 |
+
}
|
model_info.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_name": "A.X-4.0-Light MongoDB Query Generator",
|
3 |
+
"base_model": "skt/A.X-4.0-Light",
|
4 |
+
"fine_tuned_by": "Solbi",
|
5 |
+
"training_date": "2025-09-16T00:55:06.048798",
|
6 |
+
"training_method": "LoRA (Low-Rank Adaptation)",
|
7 |
+
"dataset_size": "360 samples",
|
8 |
+
"domain": "E-commerce MongoDB Queries",
|
9 |
+
"language": [
|
10 |
+
"Korean",
|
11 |
+
"English"
|
12 |
+
],
|
13 |
+
"license": "Apache-2.0"
|
14 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"<|pad|>",
|
5 |
+
"<|unk|>",
|
6 |
+
"<|sep|>",
|
7 |
+
"<|mask|>",
|
8 |
+
"<|cls|>",
|
9 |
+
"<|image|>",
|
10 |
+
"<|audio|>",
|
11 |
+
"<|user|>",
|
12 |
+
"<|system|>",
|
13 |
+
"<|assistant|>",
|
14 |
+
"<|extra_id_0|>",
|
15 |
+
"<|extra_id_1|>",
|
16 |
+
"<|extra_id_2|>",
|
17 |
+
"<|extra_id_3|>",
|
18 |
+
"<|extra_id_4|>",
|
19 |
+
"<|extra_id_5|>",
|
20 |
+
"<|extra_id_6|>",
|
21 |
+
"<|extra_id_7|>",
|
22 |
+
"<|extra_id_8|>",
|
23 |
+
"<|extra_id_9|>",
|
24 |
+
"<|extra_id_10|>",
|
25 |
+
"<|extra_id_13|>",
|
26 |
+
"<|im_start|>",
|
27 |
+
"<|im_sep|>",
|
28 |
+
"<|im_end|>",
|
29 |
+
"<|resident_reg|>",
|
30 |
+
"<|foreigner_reg|>",
|
31 |
+
"<|business_reg|>",
|
32 |
+
"<|credit_card|>",
|
33 |
+
"<|passport|>",
|
34 |
+
"<|driver_license|>",
|
35 |
+
"<|telephone|>",
|
36 |
+
"<|health_insurance|>",
|
37 |
+
"<|bank_account|>"
|
38 |
+
],
|
39 |
+
"bos_token": {
|
40 |
+
"content": "<|endoftext|>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": false,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"cls_token": {
|
47 |
+
"content": "<|cls|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false
|
52 |
+
},
|
53 |
+
"eos_token": {
|
54 |
+
"content": "<|im_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false
|
59 |
+
},
|
60 |
+
"mask_token": {
|
61 |
+
"content": "<|mask|>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false
|
66 |
+
},
|
67 |
+
"pad_token": {
|
68 |
+
"content": "<|pad|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false
|
73 |
+
},
|
74 |
+
"sep_token": {
|
75 |
+
"content": "<|sep|>",
|
76 |
+
"lstrip": false,
|
77 |
+
"normalized": false,
|
78 |
+
"rstrip": false,
|
79 |
+
"single_word": false
|
80 |
+
},
|
81 |
+
"unk_token": {
|
82 |
+
"content": "<|unk|>",
|
83 |
+
"lstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"rstrip": false,
|
86 |
+
"single_word": false
|
87 |
+
}
|
88 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,392 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<|pad|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<|unk|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<|sep|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"4": {
|
38 |
+
"content": "<|mask|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"5": {
|
46 |
+
"content": "<|cls|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"6": {
|
54 |
+
"content": "<|image|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"7": {
|
62 |
+
"content": "<|audio|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"8": {
|
70 |
+
"content": "<|user|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"9": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"10": {
|
86 |
+
"content": "<|assistant|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"11": {
|
94 |
+
"content": "<|extra_id_0|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"12": {
|
102 |
+
"content": "<|extra_id_1|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"13": {
|
110 |
+
"content": "<|extra_id_2|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"14": {
|
118 |
+
"content": "<|extra_id_3|>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": true
|
124 |
+
},
|
125 |
+
"15": {
|
126 |
+
"content": "<|extra_id_4|>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": true
|
132 |
+
},
|
133 |
+
"16": {
|
134 |
+
"content": "<|extra_id_5|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
"17": {
|
142 |
+
"content": "<|extra_id_6|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": true
|
148 |
+
},
|
149 |
+
"18": {
|
150 |
+
"content": "<|extra_id_7|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": true
|
156 |
+
},
|
157 |
+
"19": {
|
158 |
+
"content": "<|extra_id_8|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": true
|
164 |
+
},
|
165 |
+
"20": {
|
166 |
+
"content": "<|extra_id_9|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": true
|
172 |
+
},
|
173 |
+
"21": {
|
174 |
+
"content": "<|extra_id_10|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": true
|
180 |
+
},
|
181 |
+
"22": {
|
182 |
+
"content": "</think>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": false
|
188 |
+
},
|
189 |
+
"23": {
|
190 |
+
"content": "<think>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": false
|
196 |
+
},
|
197 |
+
"24": {
|
198 |
+
"content": "<|extra_id_13|>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": true
|
204 |
+
},
|
205 |
+
"25": {
|
206 |
+
"content": "<|im_start|>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": true
|
212 |
+
},
|
213 |
+
"26": {
|
214 |
+
"content": "<|im_sep|>",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false,
|
219 |
+
"special": true
|
220 |
+
},
|
221 |
+
"27": {
|
222 |
+
"content": "<|im_end|>",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": false,
|
225 |
+
"rstrip": false,
|
226 |
+
"single_word": false,
|
227 |
+
"special": true
|
228 |
+
},
|
229 |
+
"28": {
|
230 |
+
"content": "<|resident_reg|>",
|
231 |
+
"lstrip": false,
|
232 |
+
"normalized": false,
|
233 |
+
"rstrip": false,
|
234 |
+
"single_word": false,
|
235 |
+
"special": true
|
236 |
+
},
|
237 |
+
"29": {
|
238 |
+
"content": "<|foreigner_reg|>",
|
239 |
+
"lstrip": false,
|
240 |
+
"normalized": false,
|
241 |
+
"rstrip": false,
|
242 |
+
"single_word": false,
|
243 |
+
"special": true
|
244 |
+
},
|
245 |
+
"30": {
|
246 |
+
"content": "<|business_reg|>",
|
247 |
+
"lstrip": false,
|
248 |
+
"normalized": false,
|
249 |
+
"rstrip": false,
|
250 |
+
"single_word": false,
|
251 |
+
"special": true
|
252 |
+
},
|
253 |
+
"31": {
|
254 |
+
"content": "<|credit_card|>",
|
255 |
+
"lstrip": false,
|
256 |
+
"normalized": false,
|
257 |
+
"rstrip": false,
|
258 |
+
"single_word": false,
|
259 |
+
"special": true
|
260 |
+
},
|
261 |
+
"32": {
|
262 |
+
"content": "<|passport|>",
|
263 |
+
"lstrip": false,
|
264 |
+
"normalized": false,
|
265 |
+
"rstrip": false,
|
266 |
+
"single_word": false,
|
267 |
+
"special": true
|
268 |
+
},
|
269 |
+
"33": {
|
270 |
+
"content": "<|driver_license|>",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": false,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false,
|
275 |
+
"special": true
|
276 |
+
},
|
277 |
+
"34": {
|
278 |
+
"content": "<|telephone|>",
|
279 |
+
"lstrip": false,
|
280 |
+
"normalized": false,
|
281 |
+
"rstrip": false,
|
282 |
+
"single_word": false,
|
283 |
+
"special": true
|
284 |
+
},
|
285 |
+
"35": {
|
286 |
+
"content": "<|health_insurance|>",
|
287 |
+
"lstrip": false,
|
288 |
+
"normalized": false,
|
289 |
+
"rstrip": false,
|
290 |
+
"single_word": false,
|
291 |
+
"special": true
|
292 |
+
},
|
293 |
+
"36": {
|
294 |
+
"content": "<|bank_account|>",
|
295 |
+
"lstrip": false,
|
296 |
+
"normalized": false,
|
297 |
+
"rstrip": false,
|
298 |
+
"single_word": false,
|
299 |
+
"special": true
|
300 |
+
},
|
301 |
+
"37": {
|
302 |
+
"content": "</tool_output>",
|
303 |
+
"lstrip": false,
|
304 |
+
"normalized": false,
|
305 |
+
"rstrip": false,
|
306 |
+
"single_word": false,
|
307 |
+
"special": false
|
308 |
+
},
|
309 |
+
"38": {
|
310 |
+
"content": "<tool_output>",
|
311 |
+
"lstrip": false,
|
312 |
+
"normalized": false,
|
313 |
+
"rstrip": false,
|
314 |
+
"single_word": false,
|
315 |
+
"special": false
|
316 |
+
},
|
317 |
+
"39": {
|
318 |
+
"content": "</tool_call>",
|
319 |
+
"lstrip": false,
|
320 |
+
"normalized": false,
|
321 |
+
"rstrip": false,
|
322 |
+
"single_word": false,
|
323 |
+
"special": false
|
324 |
+
},
|
325 |
+
"40": {
|
326 |
+
"content": "<tool_call>",
|
327 |
+
"lstrip": false,
|
328 |
+
"normalized": false,
|
329 |
+
"rstrip": false,
|
330 |
+
"single_word": false,
|
331 |
+
"special": false
|
332 |
+
}
|
333 |
+
},
|
334 |
+
"additional_special_tokens": [
|
335 |
+
"<|endoftext|>",
|
336 |
+
"<|pad|>",
|
337 |
+
"<|unk|>",
|
338 |
+
"<|sep|>",
|
339 |
+
"<|mask|>",
|
340 |
+
"<|cls|>",
|
341 |
+
"<|image|>",
|
342 |
+
"<|audio|>",
|
343 |
+
"<|user|>",
|
344 |
+
"<|system|>",
|
345 |
+
"<|assistant|>",
|
346 |
+
"<|extra_id_0|>",
|
347 |
+
"<|extra_id_1|>",
|
348 |
+
"<|extra_id_2|>",
|
349 |
+
"<|extra_id_3|>",
|
350 |
+
"<|extra_id_4|>",
|
351 |
+
"<|extra_id_5|>",
|
352 |
+
"<|extra_id_6|>",
|
353 |
+
"<|extra_id_7|>",
|
354 |
+
"<|extra_id_8|>",
|
355 |
+
"<|extra_id_9|>",
|
356 |
+
"<|extra_id_10|>",
|
357 |
+
"<|extra_id_13|>",
|
358 |
+
"<|im_start|>",
|
359 |
+
"<|im_sep|>",
|
360 |
+
"<|im_end|>",
|
361 |
+
"<|resident_reg|>",
|
362 |
+
"<|foreigner_reg|>",
|
363 |
+
"<|business_reg|>",
|
364 |
+
"<|credit_card|>",
|
365 |
+
"<|passport|>",
|
366 |
+
"<|driver_license|>",
|
367 |
+
"<|telephone|>",
|
368 |
+
"<|health_insurance|>",
|
369 |
+
"<|bank_account|>"
|
370 |
+
],
|
371 |
+
"bos_token": "<|endoftext|>",
|
372 |
+
"clean_up_tokenization_spaces": true,
|
373 |
+
"cls_token": "<|cls|>",
|
374 |
+
"eod_token": "<|endoftext|>",
|
375 |
+
"eos_token": "<|im_end|>",
|
376 |
+
"errors": "replace",
|
377 |
+
"extra_special_tokens": {},
|
378 |
+
"mask_token": "<|mask|>",
|
379 |
+
"max_length": 1024,
|
380 |
+
"model_max_length": 16384,
|
381 |
+
"pad_to_multiple_of": null,
|
382 |
+
"pad_token": "<|pad|>",
|
383 |
+
"pad_token_type_id": 0,
|
384 |
+
"padding_side": "right",
|
385 |
+
"sep_token": "<|sep|>",
|
386 |
+
"stride": 0,
|
387 |
+
"tokenizer_class": "GPT2Tokenizer",
|
388 |
+
"truncation_side": "right",
|
389 |
+
"truncation_strategy": "longest_first",
|
390 |
+
"unk_token": "<|unk|>",
|
391 |
+
"vocab_size": 102400
|
392 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|