初始化项目,由ModelHub XC社区提供模型

Model: InfosysEnterprise/NT-Java-1.1B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-14 07:07:18 +08:00
commit d78d784e8b
9 changed files with 147418 additions and 0 deletions

30
tokenizer_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"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|>",
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>",
"vocab_size": 49152
}