初始化项目,由ModelHub XC社区提供模型

Model: Sharathhebbar24/SSH_355M
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-03 16:45:21 +08:00
commit 30be5b0156
10 changed files with 150605 additions and 0 deletions

24
tokenizer_config.json Normal file
View File

@@ -0,0 +1,24 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"max_length": 512,
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"stride": 0,
"tokenizer_class": "GPT2Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<|endoftext|>"
}