Upload mlx/tokenizer_config.json with huggingface_hub
Browse files- mlx/tokenizer_config.json +33 -1
mlx/tokenizer_config.json
CHANGED
|
@@ -177,6 +177,38 @@
|
|
| 177 |
"rstrip": false,
|
| 178 |
"single_word": false,
|
| 179 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
}
|
| 181 |
},
|
| 182 |
"additional_special_tokens": [
|
|
@@ -199,7 +231,7 @@
|
|
| 199 |
"eos_token": "<|im_end|>",
|
| 200 |
"errors": "replace",
|
| 201 |
"extra_special_tokens": {},
|
| 202 |
-
"model_max_length":
|
| 203 |
"pad_token": "<|endoftext|>",
|
| 204 |
"split_special_tokens": false,
|
| 205 |
"tokenizer_class": "Qwen2Tokenizer",
|
|
|
|
| 177 |
"rstrip": false,
|
| 178 |
"single_word": false,
|
| 179 |
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
}
|
| 213 |
},
|
| 214 |
"additional_special_tokens": [
|
|
|
|
| 231 |
"eos_token": "<|im_end|>",
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 1010000,
|
| 235 |
"pad_token": "<|endoftext|>",
|
| 236 |
"split_special_tokens": false,
|
| 237 |
"tokenizer_class": "Qwen2Tokenizer",
|