初始化项目,由ModelHub XC社区提供模型
Model: Tralalabs/TralalLM-50M Source: Original Platform
This commit is contained in:
32
tokenizer_config.json
Normal file
32
tokenizer_config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"extra_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<repo_name>",
|
||||
"<reponame>",
|
||||
"<file_sep>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<jupyter_script>",
|
||||
"<empty_output>"
|
||||
],
|
||||
"is_local": true,
|
||||
"model_max_length": 8192,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
Reference in New Issue
Block a user