Deepseek-Coder-V2-Lite-13B-Instruct-Math10K-diff-info-Distill-token-specific-scale
/
tokenizer_config.json
| { | |
| "add_bos_token": true, | |
| "add_eos_token": false, | |
| "add_prefix_space": null, | |
| "added_tokens_decoder": { | |
| "100000": { | |
| "content": "<｜begin▁of▁sentence｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "100001": { | |
| "content": "<｜end▁of▁sentence｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "100002": { | |
| "content": "<｜fim▁hole｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100003": { | |
| "content": "<｜fim▁begin｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100004": { | |
| "content": "<｜fim▁end｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100005": { | |
| "content": "<｜completion｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100006": { | |
| "content": "<｜User｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100007": { | |
| "content": "<｜Assistant｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100008": { | |
| "content": "<|EOT|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "100009": { | |
| "content": "<｜tool▁calls▁begin｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100010": { | |
| "content": "<｜tool▁calls▁end｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100011": { | |
| "content": "<｜tool▁call▁begin｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100012": { | |
| "content": "<｜tool▁call▁end｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100013": { | |
| "content": "<｜tool▁outputs▁begin｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100014": { | |
| "content": "<｜tool▁outputs▁end｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100015": { | |
| "content": "<｜tool▁output▁begin｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100016": { | |
| "content": "<｜tool▁output▁end｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "100017": { | |
| "content": "<｜tool▁sep｜>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| } | |
| }, | |
| "bos_token": "<｜begin▁of▁sentence｜>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<｜end▁of▁sentence｜>", | |
| "extra_special_tokens": {}, | |
| "fast_tokenizer": true, | |
| "legacy": true, | |
| "model_max_length": 16384, | |
| "pad_token": "<｜end▁of▁sentence｜>", | |
| "sp_model_kwargs": {}, | |
| "tokenizer_class": "LlamaTokenizerFast", | |
| "unk_token": null, | |
| "use_default_system_prompt": false | |
| } | |