deepseek-coder-6.7b-chat / tokenizer_config.json
AIGym's picture
Upload tokenizer
1485a2e
raw
history blame
4.99 kB
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"32000": {
"content": "õ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32001": {
"content": "÷",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32002": {
"content": "Á",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32003": {
"content": "ý",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32004": {
"content": "À",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32005": {
"content": "ÿ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32006": {
"content": "ø",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32007": {
"content": "ú",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32008": {
"content": "þ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32009": {
"content": "ü",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32010": {
"content": "ù",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32011": {
"content": "ö",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32012": {
"content": "û",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32013": {
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32014": {
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32015": {
"content": "<|fim▁hole|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32016": {
"content": "<|fim▁begin|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32017": {
"content": "<|fim▁end|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32018": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32019": {
"content": "<|User|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32020": {
"content": "<|Assistant|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32021": {
"content": "<|EOT|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<|begin▁of▁sentence|>",
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{%- set ns = namespace(found=false) -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.found = true -%}{%- endif -%}{%- endfor -%}{{bos_token}}{%- if not ns.found -%}{{'You are an AI assistant and you do your best to answer all questions and requests\n'}}{%- endif %}{%- for message in messages %}{%- if message['role'] == 'system' %}{{ message['content'] }}{%- else %}{%- if message['role'] == 'user' %}{{'Instruction:' + message['content'] + '\n'}}{%- else %}{{'\nOutput:' + message['content'] + '\n<|EOT|>\n'}}{%- endif %}{%- endif %}{%- endfor %}{% if add_generation_prompt %}{{'\nOutput:'}}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|end▁of▁sentence|>",
"legacy": true,
"model_max_length": 16384,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": null,
"use_default_system_prompt": false
}