llava-1.5-7b-hf-ft-mix-vsft / tokenizer_config.json
kkchaulagain's picture
Training in progress, step 26
366c382 verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"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": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<image>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"chat_template": "\n{\n \"id\": \"{{chat_id}}\",\n \"conversations\": [\n {% for message in messages %}\n {\n \"from\": \"{% if message['role'] == 'user' %}human{% else %}gpt{% endif %}\",\n \"value\": \"{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<image>{% endif %}{% endfor %}\"\n }{% if not loop.last %},{% endif %}\n {% endfor %}\n ]\n}\n",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"padding_side": "left",
"processor_class": "LlavaProcessor",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"trust_remote_code": false,
"unk_token": "<unk>",
"use_default_system_prompt": false
}