初始化项目,由ModelHub XC社区提供模型

Model: radlab/polish-gpt2-small-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-25 16:11:00 +08:00
commit 8461a3b4d0
15 changed files with 200939 additions and 0 deletions

14
tokenizer_config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"add_prefix_space": false,
"additional_special_tokens": [
"bos_token",
"eos_token",
"unk_token"
],
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1024,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}