156 lines
4.4 KiB
JSON
156 lines
4.4 KiB
JSON
{
|
|
"add_prefix_space": false,
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<|endoftext|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<|im_start|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "<|im_end|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"3": {
|
|
"content": "<repo_name>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"4": {
|
|
"content": "<reponame>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"5": {
|
|
"content": "<file_sep>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"6": {
|
|
"content": "<filename>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"7": {
|
|
"content": "<gh_stars>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"8": {
|
|
"content": "<issue_start>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"9": {
|
|
"content": "<issue_comment>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"10": {
|
|
"content": "<issue_closed>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"11": {
|
|
"content": "<jupyter_start>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"12": {
|
|
"content": "<jupyter_text>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"13": {
|
|
"content": "<jupyter_code>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"14": {
|
|
"content": "<jupyter_output>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"15": {
|
|
"content": "<jupyter_script>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"16": {
|
|
"content": "<empty_output>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"additional_special_tokens": [
|
|
"<|im_start|>",
|
|
"<|im_end|>"
|
|
],
|
|
"bos_token": "<|im_start|>",
|
|
"chat_template": "{%- set reasoning_instruction = \"Think deeply inside <think> </think> tags before responding to the user query.\\n\\nFormat:\\n\\n<think>\\nYour internal thought process here.\\n</think>\\n\\nYour response to the user here.\" -%}\n{%- set system_message = \"\" -%}\n{%- if messages[0].role == \"system\" -%}\n\t{%- set system_message = messages[0].content.rstrip() + \"\\n\\n\" -%}\n\t{%- set messages = messages[1:] -%}\n{%- endif -%}\n{%- set system_message = system_message + reasoning_instruction -%}\n{{- \"<|im_start|>system\\n\" + system_message.lstrip() + \"<|im_end|>\\n\" -}}\n{%- for message in messages -%}\n\t{{- \"<|im_start|>\" + message.role + \"\\n\" -}}\t\n\t{%- set content = message.content -%}\n\t{%- if message.role == \"assistant\" and not loop.last -%}\n\t\t{%- if \"</think>\" in message.content -%}\n\t\t\t{%- set content = content.split(\"</think>\")[-1].strip() -%}\n\t\t{%- endif -%}\n\t\t{{ \"</think>\\n\\n\" }}\n\t{%- endif -%}\n\t{{- content + \"<|im_end|>\\n\" -}}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n\t{{- \"<|im_start|>assistant\\n<think>\\n\" -}}\n{%- endif -%}",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|im_end|>",
|
|
"extra_special_tokens": {},
|
|
"model_max_length": 10240,
|
|
"pad_token": "<|im_end|>",
|
|
"tokenizer_class": "GPT2Tokenizer",
|
|
"unk_token": "<|endoftext|>",
|
|
"vocab_size": 49152
|
|
}
|