初始化项目,由ModelHub XC社区提供模型

Model: nicholasKluge/Aira-OPT-1B3
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-21 20:55:41 +08:00
commit 8ede1d2e9a
19 changed files with 150800 additions and 0 deletions

55
tokenizer_config.json Normal file
View File

@@ -0,0 +1,55 @@
{
"add_bos_token": true,
"add_prefix_space": false,
"added_tokens_decoder": {
"50265": {
"content": "<|startofinstruction|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50266": {
"content": "<|endofcompletion|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50267": {
"content": "<|unk|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50268": {
"content": "<|endofinstruction|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50269": {
"content": "<|pad|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startofinstruction|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endofcompletion|>",
"errors": "replace",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"sep_token": "<|endofinstruction|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|unk|>"
}