初始化项目,由ModelHub XC社区提供模型

Model: Data-Juicer/LLaMA-7B-EN-Chat-40k
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-17 22:23:06 +08:00
commit 11194e7de4
12 changed files with 190 additions and 0 deletions

34
tokenizer_config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1024,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}