初始化项目,由ModelHub XC社区提供模型

Model: HuggingFaceFW/ablation-exp-dedup-ind_mh-global_line-350BT
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-06 07:46:30 +08:00
commit cb6c633c34
11 changed files with 50314 additions and 0 deletions

19
tokenizer_config.json Normal file
View File

@@ -0,0 +1,19 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1024,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}