Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- special_tokens_map.json +0 -15
- tokenizer_config.json +3 -23
special_tokens_map.json
CHANGED
@@ -1,19 +1,4 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
"<|im_start|>",
|
4 |
-
"<|im_end|>",
|
5 |
-
"<|object_ref_start|>",
|
6 |
-
"<|object_ref_end|>",
|
7 |
-
"<|box_start|>",
|
8 |
-
"<|box_end|>",
|
9 |
-
"<|quad_start|>",
|
10 |
-
"<|quad_end|>",
|
11 |
-
"<|vision_start|>",
|
12 |
-
"<|vision_end|>",
|
13 |
-
"<|vision_pad|>",
|
14 |
-
"<|image_pad|>",
|
15 |
-
"<|video_pad|>"
|
16 |
-
],
|
17 |
"eos_token": {
|
18 |
"content": "<|im_end|>",
|
19 |
"lstrip": false,
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"eos_token": {
|
3 |
"content": "<|im_end|>",
|
4 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": false,
|
3 |
-
"add_prefix_space": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"151643": {
|
6 |
"content": "<|endoftext|>",
|
@@ -187,30 +185,12 @@
|
|
187 |
"special": true
|
188 |
}
|
189 |
},
|
190 |
-
"additional_special_tokens": [
|
191 |
-
"<|im_start|>",
|
192 |
-
"<|im_end|>",
|
193 |
-
"<|object_ref_start|>",
|
194 |
-
"<|object_ref_end|>",
|
195 |
-
"<|box_start|>",
|
196 |
-
"<|box_end|>",
|
197 |
-
"<|quad_start|>",
|
198 |
-
"<|quad_end|>",
|
199 |
-
"<|vision_start|>",
|
200 |
-
"<|vision_end|>",
|
201 |
-
"<|vision_pad|>",
|
202 |
-
"<|image_pad|>",
|
203 |
-
"<|video_pad|>"
|
204 |
-
],
|
205 |
"bos_token": null,
|
206 |
-
"chat_template": "{
|
207 |
-
"clean_up_tokenization_spaces":
|
208 |
"eos_token": "<|im_end|>",
|
209 |
-
"
|
210 |
-
"model_max_length": 32768,
|
211 |
"pad_token": "<|PAD_TOKEN|>",
|
212 |
-
"padding_side": "left",
|
213 |
-
"split_special_tokens": false,
|
214 |
"tokenizer_class": "Qwen2Tokenizer",
|
215 |
"unk_token": null
|
216 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"151643": {
|
4 |
"content": "<|endoftext|>",
|
|
|
185 |
"special": true
|
186 |
}
|
187 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
188 |
"bos_token": null,
|
189 |
+
"chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% endif %}",
|
190 |
+
"clean_up_tokenization_spaces": true,
|
191 |
"eos_token": "<|im_end|>",
|
192 |
+
"model_max_length": 1000000000000000019884624838656,
|
|
|
193 |
"pad_token": "<|PAD_TOKEN|>",
|
|
|
|
|
194 |
"tokenizer_class": "Qwen2Tokenizer",
|
195 |
"unk_token": null
|
196 |
}
|