Fix EOS in special_tokens_map.json

This commit is contained in:
ai-modelscope
2025-01-13 21:10:32 +08:00
parent 696218803c
commit b4e77e7940
13 changed files with 66082 additions and 57 deletions

35
tokenizer_config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<begin▁of▁sentence>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "<|EOT|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"legacy": true,
"model_max_length": 16384,
"pad_token": {
"__type": "AddedToken",
"content": "<end▁of▁sentence>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sp_model_kwargs": {},
"unk_token": null,
"tokenizer_class": "LlamaTokenizerFast",
"chat_template": "{%- set found_item = false -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set found_item = true -%}\n {%- endif -%}\n{%- endfor -%}\n{%- if not found_item -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{{'### Response:\\n'}}\n"
}