初始化项目,由ModelHub XC社区提供模型
Model: open-sci/sft__ot30k_SmolLM2-1.7B-16k-SFT-Tulu3-decontaminated Source: Original Platform
This commit is contained in:
19
tokenizer_config.json
Normal file
19
tokenizer_config.json
Normal file
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<end_of_turn>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {
|
||||
"<|im_end|>": "<|im_end|>"
|
||||
},
|
||||
"is_local": true,
|
||||
"model_max_length": 16384,
|
||||
"pad_token": "<end_of_turn>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
Reference in New Issue
Block a user