bueble-lm-2b-sft / tokenizer_config.json
johannhartmann's picture
Upload folder using huggingface_hub
0c1bc02 verified
{
"add_bos_token": true,
"add_eos_token": true,
"add_prefix_space": null,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"5": {
"content": "▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"6": {
"content": "▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"7": {
"content": "▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"8": {
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"9": {
"content": "--",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"10": {
"content": "----",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"11": {
"content": "-----",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"12": {
"content": "--------",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"13": {
"content": "----------------",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"14": {
"content": "++",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"15": {
"content": "/**",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"16": {
"content": "***",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"17": {
"content": "****",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"18": {
"content": "******",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"19": {
"content": "********",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"20": {
"content": "**/",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"21": {
"content": "##",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"22": {
"content": "###",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"23": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"24": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"25": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"26": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"27": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"28": {
"content": "▁—",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"29": {
"content": "▁“",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"30": {
"content": "“",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"31": {
"content": "”",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"32": {
"content": "’",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"33": {
"content": "—",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"34": {
"content": "{",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"35": {
"content": "}\"",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"36": {
"content": "{\"",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"37": {
"content": "}",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"20000": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20001": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20002": {
"content": "<|start_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20003": {
"content": "<|end_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20004": {
"content": "<|eom_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"20005": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|begin_of_text|>",
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
"clean_up_tokenization_spaces": true,
"eos_token": "<|eot_id|>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|eot_id|>",
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"split_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}