tangled-alpha-0.2-core / tokenizer_config.json
mtasic85's picture
pretrain core
5b81e55
raw
history blame
5.73 kB
{
"add_bos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"32000": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32002": {
"content": "<|placeholder1|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32003": {
"content": "<|placeholder2|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32004": {
"content": "<|placeholder3|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32005": {
"content": "<|placeholder4|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32006": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32007": {
"content": "<|end|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32008": {
"content": "<|placeholder5|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32009": {
"content": "<|placeholder6|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32010": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32011": {
"content": "<tools>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32012": {
"content": "</tools>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32013": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32014": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32015": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32016": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32017": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32018": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>' + message['content'] + '<|end|>'}}{% elif message['role'] == 'user' %}{{'<|user|>' + message['content'] + '<|end|>'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>' + message['content'] + '<|end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "left",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}