1.1.0

v1.1.0版本

1. 新增了基于Qwen2.5的中文文本纠错模型，支持多字、少字、错字、词序、语法等错误纠正，发布了shibing624/chinese-text-correction-1.5b和shibing624/chinese-text-correction-7b模型，及其对应的LoRA模型。

模型效果评估：

Full Changelog: 1.0.2...1.1.0

1.0.2

What's Changed

• Llm by @shibing624 in #431
• Llm by @shibing624 in #432
• 库依赖跟新和最低版本要求更新 by @Vela-zz in #444
• Fix issue #470: Improve how confusion words are located and/or replaced by @treya-lin in #471

New Contributors

• @Vela-zz made their first contribution in #444
• @treya-lin made their first contribution in #471

Full Changelog: 1.0.0...1.0.2

1.0.0

v1.0.0版本

1. 新增了ChatGLM3/LLaMA2等GPT模型用于中文文本纠错，发布了基于ChatGLM3-6B的shibing624/chatglm3-6b-csc-chinese-lora拼写和语法纠错模型；
2. 重写了DeepContext、ConvSeq2Seq、T5等模型的实现。

Full Changelog: 0.4.8...1.0.0

0.4.6

Full Changelog: 0.4.5...0.4.6

0.4.5

Full Changelog: 0.4.4...0.4.5

0.4.3

What's Changed

• Add ernie-csc model by @joey12300 in #252
• Update: the description for MacBERT. by @okcd00 in #259
• Solve the misalignment problem on UNK tokens (MacBERT). by @okcd00 in #261

New Contributors

• @joey12300 made their first contribution in #252
• @okcd00 made their first contribution in #259

Full Changelog: 0.4.1...0.4.3

0.3.1

0.3.1,__init__ delete torch import.

0.2.4

update demo.