初始化项目,由ModelHub XC社区提供模型

Model: lgb35/B-GPT-es-fineweb-beginner-alpacaEnglish
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-08 10:31:18 +08:00
commit 65f33de5d3
7 changed files with 250607 additions and 0 deletions

12
tokenizer_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": false,
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}