初始化项目,由ModelHub XC社区提供模型

Model: NYTK/PULI-GPT-2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-01 13:47:43 +08:00
commit a2b0b01e72
9 changed files with 149621 additions and 0 deletions

1
tokenizer_config.json Normal file
View File

@@ -0,0 +1 @@
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "/home/yanggy/CORPORA/PULI/corpora/vocab/GPT-vocab/25B/autovocab", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}