初始化项目,由ModelHub XC社区提供模型

Model: cs1090b/hw5-part3-sft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-29 12:33:29 +08:00
commit eba0f52387
7 changed files with 250613 additions and 0 deletions

16
tokenizer_config.json Normal file
View File

@@ -0,0 +1,16 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": true,
"max_length": 1024,
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"stride": 0,
"tokenizer_class": "GPT2Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<|endoftext|>"
}