tokenizer_config.json

{
 "add_bos_token": false,
 "add_eos_token": true,
 "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": "<|im_start|>",
 "lstrip": false,
 "normalized": true,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "32001": {
 "content": "<|im_end|>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "32002": {
 "content": "\n",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": false
 },
 "32003": {
 "content": "<|fim_prefix|>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "32004": {
 "content": "<|fim_middle|>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "32005": {
 "content": "<|fim_suffix|>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "32006": {
 "content": "<|file_separator|>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "32007": {
 "content": "<|startofthought|>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "32008": {
 "content": "<|endofthought|>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 }
 },
 "additional_special_tokens": [
 "<|im_start|>",
 "<|im_end|>",
 "<|fim_prefix|>",
 "<|fim_middle|>",
 "<|fim_suffix|>",
 "<|file_separator|>",
 "<|startofthought|>",
 "<|endofthought|>"
 ],
 "bos_token": "<s>",
 "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '\\n<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '\\n<|im_end|>\\n' + '<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '\\n<|im_end|>\\n' }}{% endif %}{% endfor %}",
 "clean_up_tokenization_spaces": true,
 "cls_token": "</s>",
 "eos_token": "</s>",
 "legacy": true,
 "model_max_length": 1000000000000000019884624838656,
 "pad_token": "<unk>",
 "padding_side": "right",
 "sep_token": "\n",
 "sp_model_kwargs": {},
 "spaces_between_special_tokens": false,
 "split_special_tokens": false,
 "tokenizer_class": "LlamaTokenizer",
 "unk_token": "<unk>",
 "use_default_system_prompt": false,
 "use_fast": false
}