DeepSeek-R1-0528-Qwen3-8B / tokenizer_config.json
danielhanchen's picture
Upload folder using huggingface_hub
af7f9f9 verified
{
"add_bos_token": false,
"add_eos_token": false,
"add_prefix_space": null,
"added_tokens_decoder": {
"151643": {
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151669": {
"content": "<|User|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151670": {
"content": "<|Assistant|>",
"lstrip": false,
"normalized": false,
"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": {},
"legacy": true,
"model_max_length": 131072,
"pad_token": "<|vision_pad|>",
"padding_side": "left",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizerFast",
"unk_token": null,
"use_default_system_prompt": false,
"chat_template": "{%- if not add_generation_prompt is defined %}\n {%- set add_generation_prompt = false %}\n{%- endif %}\n{%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n {%- if ns.is_first_sp %}\n {%- set ns.system_prompt = ns.system_prompt + message['content'] %}\n {%- set ns.is_first_sp = false %}\n {%- else %}\n {%- set ns.system_prompt = ns.system_prompt + '\\n\\n' + message['content'] %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n\n{#- Adapted from https://github.com/sgl-project/sglang/blob/main/examples/chat_template/tool_chat_template_deepseekr1.jinja #}\n{%- if tools is defined and tools is not none %}\n {%- set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\\n' + '<|tool▁calls▁begin|><|tool▁call▁begin|>function<|tool▁sep|>FUNCTION_NAME\\n' + '```json\\n{\"param1\": \"value1\", \"param2\": \"value2\"}\\n```<|tool▁call▁end|><|tool▁calls▁end|>\\n\\n' + 'Make sure the JSON is valid.' + '## Tools\\n\\n### Function\\n\\nYou have the following functions available:\\n\\n') %}\n {%- for tool in tools %}\n {%- set tool_ns.text = tool_ns.text + '\\n```json\\n' + (tool | tojson) + '\\n```\\n' %}\n {%- endfor %}\n {%- if ns.system_prompt|length != 0 %}\n {%- set ns.system_prompt = ns.system_prompt + '\\n\\n' + tool_ns.text %}\n {%- else %}\n {%- set ns.system_prompt = tool_ns.text %}\n {%- endif %}\n{%- endif %}\n{{- bos_token }}\n{{- ns.system_prompt }}\n{%- set last_index = (messages|length - 1) %}\n{%- for message in messages %}\n {%- set content = message['content'] %}\n {%- if message['role'] == 'user' %}\n {%- set ns.is_tool = false -%}\n {%- set ns.is_first = false -%}\n {%- set ns.is_last_user = true -%}\n {%- if loop.index0 == last_index %}\n {{- '<|User|>' + content }}\n {%- else %}\n {{- '<|User|>' + content + '<|Assistant|>'}}\n {%- endif %}\n {%- endif %}\n {%- if message['role'] == 'assistant' %}\n {%- if '</think>' in content %}\n {%- set content = (content.split('</think>')|last) %}\n {%- endif %}\n {%- endif %}\n {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}\n {%- set ns.is_last_user = false -%}\n {%- if ns.is_tool %}\n {{- '<|tool▁outputs▁end|>'}}\n {%- endif %}\n {%- set ns.is_first = false %}\n {%- set ns.is_tool = false -%}\n {%- set ns.is_output_first = true %}\n {%- for tool in message['tool_calls'] %}\n {%- set arguments = tool['function']['arguments'] %}\n {%- if arguments is not string %}\n {%- set arguments = arguments|tojson %}\n {%- endif %}\n {%- if not ns.is_first %}\n {%- if content is none %}\n {{- '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + arguments + '\\n' + '```' + '<|tool▁call▁end|>'}}\n }\n {%- else %}\n {{- content + '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + arguments + '\\n' + '```' + '<|tool▁call▁end|>'}}\n {%- endif %}\n {%- set ns.is_first = true -%}\n {%- else %}\n {{- '\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + arguments + '\\n' + '```' + '<|tool▁call▁end|>'}}\n {%- endif %}\n {%- endfor %}\n {{- '<|tool▁calls▁end|><|end▁of▁sentence|>'}}\n {%- endif %}\n {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}\n {%- set ns.is_last_user = false -%}\n {%- if ns.is_tool %}\n {{- '<|tool▁outputs▁end|>' + content + '<|end▁of▁sentence|>'}}\n {%- set ns.is_tool = false -%}\n {%- else %}\n {{- content + '<|end▁of▁sentence|>'}}\n {%- endif %}\n {%- endif %}\n {%- if message['role'] == 'tool' %}\n {%- set ns.is_last_user = false -%}\n {%- set ns.is_tool = true -%}\n {%- if ns.is_output_first %}\n {{- '<|tool▁outputs▁begin|><|tool▁output▁begin|>' + content + '<|tool▁output▁end|>'}}\n {%- set ns.is_output_first = false %}\n {%- else %}\n {{- '\\n<|tool▁output▁begin|>' + content + '<|tool▁output▁end|>'}}\n {%- endif %}\n {%- endif %}\n{%- endfor -%}\n{%- if ns.is_tool %}\n {{- '<|tool▁outputs▁end|>'}}\n{%- endif %}\n{#- if add_generation_prompt and not ns.is_last_user and not ns.is_tool #}\n{%- if add_generation_prompt and not ns.is_tool %}\n {{- '<|Assistant|>'}}\n{%- endif %}"
}