Skip to content

🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.

13.0 KB
Raw Blame
{
    "add_bos_token": false,
    "add_eos_token": false,
    "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": "<|object_ref_start|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "4": {
            "content": "<|object_ref_end|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "5": {
            "content": "<|box_start|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "6": {
            "content": "<|box_end|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "7": {
            "content": "<|quad_start|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "8": {
            "content": "<|quad_end|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "9": {
            "content": "<|vision_start|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "10": {
            "content": "<|vision_end|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "11": {
            "content": "<|vision_pad|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "12": {
            "content": "<|image_pad|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "13": {
            "content": "<|video_pad|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "14": {
            "content": "<|audio_start|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "15": {
            "content": "<|audio_end|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "16": {
            "content": "<|audio_pad|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "17": {
            "content": "<tts_pad>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "18": {
            "content": "<tts_text_bos>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "19": {
            "content": "<tts_text_eod>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "20": {
            "content": "<tts_text_bos_single>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "21": {
            "content": "<tool_call>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "22": {
            "content": "</tool_call>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "23": {
            "content": "<tool_response>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "24": {
            "content": "</tool_response>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "25": {
            "content": "<think>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "26": {
            "content": "</think>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "27": {
            "content": "<|buffer1|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "28": {
            "content": "<|buffer2|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "29": {
            "content": "<|buffer3|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "30": {
            "content": "<|buffer4|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "31": {
            "content": "<|buffer5|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "32": {
            "content": "<|buffer6|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "33": {
            "content": "<|buffer7|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "34": {
            "content": "<|buffer8|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        },
        "35": {
            "content": "<|buffer9|>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": false
        }
    },
    "additional_special_tokens": [
        "<|im_start|>",
        "<|im_end|>",
        "<|object_ref_start|>",
        "<|object_ref_end|>",
        "<|box_start|>",
        "<|box_end|>",
        "<|quad_start|>",
        "<|quad_end|>",
        "<|vision_start|>",
        "<|vision_end|>",
        "<|vision_pad|>",
        "<|image_pad|>",
        "<|video_pad|>",
        "<|audio_start|>",
        "<|audio_end|>",
        "<|audio_pad|>",
        "<tts_pad>",
        "<tts_text_bos>",
        "<tts_text_eod>",
        "<tts_text_bos_single>"
    ],
    "bos_token": "<|im_start|>",
    "clean_up_tokenization_spaces": false,
    "eos_token": "<|im_end|>",
    "legacy": true,
    "model_max_length": 131072,
    "pad_token": "<|endoftext|>",
    "sp_model_kwargs": {},
    "spaces_between_special_tokens": false,
    "unk_token": "<|endoftext|>",
    "image_token": "<|image_pad|>",
    "audio_token": "<|audio_pad|>",
    "video_token": "<|video_pad|>",
    "vision_bos_token": "<|vision_start|>",
    "vision_eos_token": "<|vision_end|>",
    "audio_bos_token": "<|audio_start|>",
    "audio_eos_token": "<|audio_end|>",
    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\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\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if true %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if open_thinking is defined and open_thinking is true %}\n        {{- '<think>\\n' }}\n    {%- else %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
    "tokenizer_class": "PreTrainedTokenizerFast"
}