初始化项目，由ModelHub XC社区提供模型

Model: Callmeyash11/legal-clean-model Source: Original Platform
2026-08-11 14:23:17 +08:00
commit e39ab1276d
9 changed files with 395 additions and 0 deletions
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "model_max_length": 2048,
+  "padding_side": "left",
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot_id|>",
+  "pad_token": "<|eot_id|>",
+  "unk_token": "<unk>"
+}