commit 3cbc71ef4f4dbf57095ab97b98879661e4f7e749 Author: ModelHub XC Date: Wed Oct 14 13:32:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/chinese-text-correction-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..627ab34 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chinese-text-correction-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3d649fe --- /dev/null +++ b/README.md @@ -0,0 +1,181 @@ + +--- + +library_name: transformers +base_model: Qwen/Qwen2.5-7B-Instruct +license: apache-2.0 +datasets: +- shibing624/chinese_text_correction +language: +- zh +metrics: +- f1 +tags: +- text-generation-inference +widget: +- text: "文本纠错：\n少先队员因该为老人让坐。" + +--- + +[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory) + + +# QuantFactory/chinese-text-correction-7b-GGUF +This is quantized version of [shibing624/chinese-text-correction-7b](https://huggingface.co/shibing624/chinese-text-correction-7b) created using llama.cpp + +# Original Model Card + + + + +# Chinese Text Correction Model +中文文本纠错模型chinese-text-correction-7b：用于拼写纠错、语法纠错 + +`shibing624/chinese-text-correction-7b` evaluate test data： + +The overall performance of CSC **test**: + +|input_text|predict_text| +|:--- |:--- | +|文本纠错：\n少先队员因该为老人让坐。|少先队员应该为老人让座。| + +# Models + +| Name | Base Model | Download | +|-----------------|-------------------|-----------------------------------------------------------------------| +| chinese-text-correction-1.5b | Qwen/Qwen2.5-1.5B-Instruct | [🤗 Hugging Face](https://huggingface.co/shibing624/chinese-text-correction-1.5b) | +| chinese-text-correction-1.5b-lora | Qwen/Qwen2.5-1.5B-Instruct | [🤗 Hugging Face](https://huggingface.co/shibing624/chinese-text-correction-1.5b-lora) | +| chinese-text-correction-7b | Qwen/Qwen2.5-7B-Instruct | [🤗 Hugging Face](https://huggingface.co/shibing624/chinese-text-correction-7b) | +| chinese-text-correction-7b-lora | Qwen/Qwen2.5-7B-Instruct | [🤗 Hugging Face](https://huggingface.co/shibing624/chinese-text-correction-7b-lora) | + + +### 评估结果 +- 评估指标：F1 +- CSC(Chinese Spelling Correction): 拼写纠错模型，表示模型可以处理音似、形似、语法等长度对齐的错误纠正 +- CTC(CHinese Text Correction): 文本纠错模型，表示模型支持拼写、语法等长度对齐的错误纠正，还可以处理多字、少字等长度不对齐的错误纠正 +- GPU：Tesla V100，显存 32 GB + +| Model Name | Model Link | Base Model | Avg | SIGHAN-2015 | EC-LAW | MCSC | GPU/CPU | QPS | +|:-----------------|:------------------------------------------------------------------------------------------------------------------------|:---------------------------|:-----------|:------------|:-------|:-------|:--------|:--------| +| Kenlm-CSC | [shibing624/chinese-kenlm-klm](https://huggingface.co/shibing624/chinese-kenlm-klm) | kenlm | 0.3409 | 0.3147 | 0.3763 | 0.3317 | CPU | 9 | +| Mengzi-T5-CSC | [shibing624/mengzi-t5-base-chinese-correction](https://huggingface.co/shibing624/mengzi-t5-base-chinese-correction) | mengzi-t5-base | 0.3984 | 0.7758 | 0.3156 | 0.1039 | GPU | 214 | +| ERNIE-CSC | [PaddleNLP/ernie-csc](https://github.com/PaddlePaddle/PaddleNLP/tree/develop/legacy/examples/text_correction/ernie-csc) | PaddlePaddle/ernie-1.0-base-zh | 0.4353 | 0.8383 | 0.3357 | 0.1318 | GPU | 114 | +| MacBERT-CSC | [shibing624/macbert4csc-base-chinese](https://huggingface.co/shibing624/macbert4csc-base-chinese) | hfl/chinese-macbert-base | 0.3993 | 0.8314 | 0.1610 | 0.2055 | GPU | **224** | +| ChatGLM3-6B-CSC | [shibing624/chatglm3-6b-csc-chinese-lora](https://huggingface.co/shibing624/chatglm3-6b-csc-chinese-lora) | THUDM/chatglm3-6b | 0.4538 | 0.6572 | 0.4369 | 0.2672 | GPU | 3 | +| Qwen2.5-1.5B-CTC | [shibing624/chinese-text-correction-1.5b](https://huggingface.co/shibing624/chinese-text-correction-1.5b) | Qwen/Qwen2.5-1.5B-Instruct | 0.6802 | 0.3032 | 0.7846 | 0.9529 | GPU | 6 | +| Qwen2.5-7B-CTC | [shibing624/chinese-text-correction-7b](https://huggingface.co/shibing624/chinese-text-correction-7b) | Qwen/Qwen2.5-7B-Instruct | **0.8225** | 0.4917 | 0.9798 | 0.9959 | GPU | 3 | + +## Usage (pycorrector) + +本项目开源在`pycorrector`项目：[pycorrector](https://github.com/shibing624/pycorrector)，可支持大模型微调后用于文本纠错，通过如下命令调用： + +Install package: +```shell +pip install -U pycorrector +``` + +```python +from pycorrector.gpt.gpt_corrector import GptCorrector + +if __name__ == '__main__': + error_sentences = [ + '真麻烦你了。希望你们好好的跳无', + '少先队员因该为老人让坐', + '机七学习是人工智能领遇最能体现智能的一个分知', + '一只小鱼船浮在平净的河面上', + '我的家乡是有明的渔米之乡', + ] + m = GptCorrector("shibing624/chinese-text-correction-7b") + + batch_res = m.correct_batch(error_sentences) + for i in batch_res: + print(i) + print() +``` + +## Usage (HuggingFace Transformers) +Without [pycorrector](https://github.com/shibing624/pycorrector), you can use the model like this: + +First, you pass your input through the transformer model, then you get the generated sentence. + +Install package: +``` +pip install transformers +``` + +```python +# pip install transformers +from transformers import AutoModelForCausalLM, AutoTokenizer +checkpoint = "shibing624/chinese-text-correction-7b" + +device = "cuda" # for GPU usage or "cpu" for CPU usage +tokenizer = AutoTokenizer.from_pretrained(checkpoint) +model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device) + +input_content = "文本纠错：\n少先队员因该为老人让坐。" + +messages = [{"role": "user", "content": input_content}] +input_text=tokenizer.apply_chat_template(messages, tokenize=False) + +print(input_text) + +inputs = tokenizer.encode(input_text, return_tensors="pt").to(device) +outputs = model.generate(inputs, max_new_tokens=1024, temperature=0, do_sample=False, repetition_penalty=1.08) + +print(tokenizer.decode(outputs[0])) +``` + +output: +```shell +少先队员应该为老人让座。 +``` + + +模型文件组成： +``` +shibing624/chinese-text-correction-7b +|-- added_tokens.json +|-- config.json +|-- generation_config.json +|-- merges.txt +|-- model.safetensors +|-- model.safetensors.index.json +|-- README.md +|-- special_tokens_map.json +|-- tokenizer_config.json +|-- tokenizer.json +`-- vocab.json +``` + +#### 训练参数： + +- num_epochs: 8 +- batch_size: 2 +- steps: 36000 +- eval_loss: 0.12 +- base model: Qwen/Qwen2.5-7B-Instruct +- train data: [shibing624/chinese_text_correction](https://huggingface.co/datasets/shibing624/chinese_text_correction) +- train time: 10 days +- eval_loss: ![](https://huggingface.co/shibing624/chinese-text-correction-7b-lora/resolve/main/eval_loss_7b.png) +- train_loss: ![](https://huggingface.co/shibing624/chinese-text-correction-7b-lora/resolve/main/train_loss_7b.png) + +### 训练数据集 +#### 中文纠错数据集 + +- 数据：[shibing624/chinese_text_correction](https://huggingface.co/datasets/shibing624/chinese_text_correction) + + +如果需要训练Qwen的纠错模型，请参考[https://github.com/shibing624/pycorrector](https://github.com/shibing624/pycorrector) 或者 [https://github.com/shibing624/MedicalGPT](https://github.com/shibing624/MedicalGPT) + +## Citation + +```latex +@software{pycorrector, + author = {Xu Ming}, + title = {pycorrector: Implementation of language model finetune}, + year = {2024}, + url = {https://github.com/shibing624/pycorrector}, +} +``` + + diff --git a/chinese-text-correction-7b.Q2_K.gguf b/chinese-text-correction-7b.Q2_K.gguf new file mode 100644 index 0000000..3801768 --- /dev/null +++ b/chinese-text-correction-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c0e2326d01d5442274faf5d1aa90dc7186daa6c0b8f8c69121561aad9218beb +size 3015940544 diff --git a/chinese-text-correction-7b.Q3_K_L.gguf b/chinese-text-correction-7b.Q3_K_L.gguf new file mode 100644 index 0000000..a35a44f --- /dev/null +++ b/chinese-text-correction-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf142a21b86a09eed1ef25c5c1c5d3acce05ae69e8ed168ea5b6afcb49b826b +size 4088459712 diff --git a/chinese-text-correction-7b.Q3_K_M.gguf b/chinese-text-correction-7b.Q3_K_M.gguf new file mode 100644 index 0000000..426c424 --- /dev/null +++ b/chinese-text-correction-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29f42b8c51b919a942ada3b21926f6c715d606b4901b9aa276950d623413737a +size 3808391616 diff --git a/chinese-text-correction-7b.Q3_K_S.gguf b/chinese-text-correction-7b.Q3_K_S.gguf new file mode 100644 index 0000000..d0e80bf --- /dev/null +++ b/chinese-text-correction-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc63183f4f890f8fa6ddf1a92d0edf4ce09c9545fa0000f1e5d84b90af17ec1e +size 3492368832 diff --git a/chinese-text-correction-7b.Q4_0.gguf b/chinese-text-correction-7b.Q4_0.gguf new file mode 100644 index 0000000..59494d4 --- /dev/null +++ b/chinese-text-correction-7b.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3043599565aaf9ad38871569c6474cac2e06a2ba96f7b77a0aaf55176630ac0 +size 4431391168 diff --git a/chinese-text-correction-7b.Q4_1.gguf b/chinese-text-correction-7b.Q4_1.gguf new file mode 100644 index 0000000..6e69f77 --- /dev/null +++ b/chinese-text-correction-7b.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2efc9b473d144500c92c377b63abc5c17996874e88e3a04e7b10d9647e5a3e58 +size 4873284032 diff --git a/chinese-text-correction-7b.Q4_K_M.gguf b/chinese-text-correction-7b.Q4_K_M.gguf new file mode 100644 index 0000000..6d1f2cf --- /dev/null +++ b/chinese-text-correction-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7547d4ab4636b263d9b7f76e4b35ed1699702c349c5718e39df08d49fafef5d9 +size 4683073984 diff --git a/chinese-text-correction-7b.Q4_K_S.gguf b/chinese-text-correction-7b.Q4_K_S.gguf new file mode 100644 index 0000000..3c1b9c3 --- /dev/null +++ b/chinese-text-correction-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:277121dd65dfa93f7231e46488bbf14716e57b1c68b78ff1bfd5580f7965e22d +size 4457769408 diff --git a/chinese-text-correction-7b.Q5_0.gguf b/chinese-text-correction-7b.Q5_0.gguf new file mode 100644 index 0000000..ed83442 --- /dev/null +++ b/chinese-text-correction-7b.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a1629a505191f0318702cb621c07d387501c445ccc1e4e448b7e54ce8dd520 +size 5315176896 diff --git a/chinese-text-correction-7b.Q5_1.gguf b/chinese-text-correction-7b.Q5_1.gguf new file mode 100644 index 0000000..ee2664b --- /dev/null +++ b/chinese-text-correction-7b.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c280de35575cffbe9178a46015c9016e781533174e4c8b05002b2759d753ab82 +size 5757069760 diff --git a/chinese-text-correction-7b.Q5_K_M.gguf b/chinese-text-correction-7b.Q5_K_M.gguf new file mode 100644 index 0000000..23d587d --- /dev/null +++ b/chinese-text-correction-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8ed7b56bc19f9f27058130c61a3016a7b038b35950a78cc11fb10e1d89252f7 +size 5444831680 diff --git a/chinese-text-correction-7b.Q5_K_S.gguf b/chinese-text-correction-7b.Q5_K_S.gguf new file mode 100644 index 0000000..8c203cc --- /dev/null +++ b/chinese-text-correction-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22105df67f28a44025fdea3ae032cfa807f458dc0df91935ab8304a70b293e9a +size 5315176896 diff --git a/chinese-text-correction-7b.Q6_K.gguf b/chinese-text-correction-7b.Q6_K.gguf new file mode 100644 index 0000000..5f0110f --- /dev/null +++ b/chinese-text-correction-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec50833e71c921e72522e7eb1a5362e5a9ff5d43eba5aa8ee71f5f05b4be1387 +size 6254199232 diff --git a/chinese-text-correction-7b.Q8_0.gguf b/chinese-text-correction-7b.Q8_0.gguf new file mode 100644 index 0000000..0b249fc --- /dev/null +++ b/chinese-text-correction-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a13926e8c69400e20f2f20c7c13294b58bd17f3101da4956155fe34bdd4c777 +size 8098525632 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file