Upload tokenizer tokenizer_config.json
Browse files- tokenizer_config.json +60 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"32768": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"32769": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"32770": {
|
| 29 |
+
"content": "<think>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"32771": {
|
| 37 |
+
"content": "</think>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"additional_special_tokens": [
|
| 46 |
+
"<|im_start|>",
|
| 47 |
+
"<|im_end|>"
|
| 48 |
+
],
|
| 49 |
+
"bos_token": null,
|
| 50 |
+
"eos_token": "<|im_end|>",
|
| 51 |
+
"pad_token": "<|endoftext|>",
|
| 52 |
+
"unk_token": null,
|
| 53 |
+
"chat_template": "{%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n{%- endif %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>user\\n' + content + '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set has_think = false %}\n {%- set think_content = '' %}\n {%- set main_content = content %}\n \n {%- if '</think>' in content %}\n {%- set think_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set main_content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- set has_think = true %}\n {%- endif %}\n \n {{- '<|im_start|>assistant\\n' }}\n {%- if has_think %}\n {{- '<think>\\n' + think_content + '\\n</think>\\n\\n' + main_content }}\n {%- else %}\n {{- content }}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
|
| 54 |
+
"clean_up_tokenization_spaces": false,
|
| 55 |
+
"errors": "replace",
|
| 56 |
+
"model_max_length": 32768,
|
| 57 |
+
"split_special_tokens": false,
|
| 58 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 59 |
+
"add_bos_token": false
|
| 60 |
+
}
|