初始化项目,由ModelHub XC社区提供模型

Model: bigcode/starcoder-cxso
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-04 00:10:37 +08:00
commit f5d768222b
15 changed files with 49557 additions and 0 deletions

31
tokenizer_config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"add_prefix_space": false,
"additional_special_tokens": [
"<|endoftext|>",
"<fim_prefix>",
"<fim_middle>",
"<fim_suffix>",
"<fim_pad>",
"<filename>",
"<gh_stars>",
"<issue_start>",
"<issue_comment>",
"<issue_closed>",
"<jupyter_start>",
"<jupyter_text>",
"<jupyter_code>",
"<jupyter_output>",
"<empty_output>",
"<commit_before>",
"<commit_msg>",
"<commit_after>",
"<reponame>"
],
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>",
"vocab_size": 49152
}