初始化项目,由ModelHub XC社区提供模型

Model: minpeter/tiny-ko-187m-sft-250725
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-04 20:35:59 +08:00
commit 450df012ca
10 changed files with 159582 additions and 0 deletions

103
tokenizer_config.json Normal file
View File

@@ -0,0 +1,103 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"31989": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"31990": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"31991": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"31992": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"31993": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"31994": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"31995": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"31996": {
"content": "<|unused_special_token_0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"31997": {
"content": "<|unused_special_token_1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"31998": {
"content": "<|unused_special_token_2|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"31999": {
"content": "<|unused_special_token_3|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<|endoftext|>"
}