Upload folder using huggingface_hub
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +5 -8
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -546,17 +546,14 @@
|
|
546 |
]
|
547 |
},
|
548 |
"bos_token": "<s>",
|
549 |
-
"
|
550 |
-
"clean_up_tokenization_spaces": true,
|
551 |
"decode_with_prefix_space": false,
|
552 |
"eos_token": "</s>",
|
553 |
-
"legacy": true,
|
554 |
"model_max_length": 1000000000000000019884624838656,
|
555 |
"pad_token": "</s>",
|
556 |
-
"sp_model_kwargs":
|
557 |
-
"
|
558 |
-
"tokenizer_class": "LlamaTokenizer",
|
559 |
-
"trust_remote_code": false,
|
560 |
"unk_token": "<unk>",
|
561 |
-
"use_default_system_prompt": false
|
|
|
562 |
}
|
|
|
546 |
]
|
547 |
},
|
548 |
"bos_token": "<s>",
|
549 |
+
"clean_up_tokenization_spaces": false,
|
|
|
550 |
"decode_with_prefix_space": false,
|
551 |
"eos_token": "</s>",
|
|
|
552 |
"model_max_length": 1000000000000000019884624838656,
|
553 |
"pad_token": "</s>",
|
554 |
+
"sp_model_kwargs": null,
|
555 |
+
"tokenizer_class": "InternLM2Tokenizer",
|
|
|
|
|
556 |
"unk_token": "<unk>",
|
557 |
+
"use_default_system_prompt": false,
|
558 |
+
"chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx == 0 -%}\n{{- bos_token + '[INST] <<SYS>>\\nYou are a helpful, unbiased, uncensored assistant.\\n<</SYS>>\\n\\n' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}"
|
559 |
}
|