初始化项目，由ModelHub XC社区提供模型

Model: RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,54 @@
+*.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-1.5b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+chinese-text-correction-1.5b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,210 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+chinese-text-correction-1.5b - GGUF
+- Model creator: https://huggingface.co/shibing624/
+- Original model: https://huggingface.co/shibing624/chinese-text-correction-1.5b/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [chinese-text-correction-1.5b.Q2_K.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q2_K.gguf) | Q2_K | 0.63GB |
+| [chinese-text-correction-1.5b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q3_K_S.gguf) | Q3_K_S | 0.71GB |
+| [chinese-text-correction-1.5b.Q3_K.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q3_K.gguf) | Q3_K | 0.77GB |
+| [chinese-text-correction-1.5b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q3_K_M.gguf) | Q3_K_M | 0.77GB |
+| [chinese-text-correction-1.5b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q3_K_L.gguf) | Q3_K_L | 0.82GB |
+| [chinese-text-correction-1.5b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.IQ4_XS.gguf) | IQ4_XS | 0.84GB |
+| [chinese-text-correction-1.5b.Q4_0.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q4_0.gguf) | Q4_0 | 0.87GB |
+| [chinese-text-correction-1.5b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.IQ4_NL.gguf) | IQ4_NL | 0.88GB |
+| [chinese-text-correction-1.5b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q4_K_S.gguf) | Q4_K_S | 0.88GB |
+| [chinese-text-correction-1.5b.Q4_K.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q4_K.gguf) | Q4_K | 0.92GB |
+| [chinese-text-correction-1.5b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q4_K_M.gguf) | Q4_K_M | 0.92GB |
+| [chinese-text-correction-1.5b.Q4_1.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q4_1.gguf) | Q4_1 | 0.95GB |
+| [chinese-text-correction-1.5b.Q5_0.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q5_0.gguf) | Q5_0 | 1.02GB |
+| [chinese-text-correction-1.5b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q5_K_S.gguf) | Q5_K_S | 1.02GB |
+| [chinese-text-correction-1.5b.Q5_K.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q5_K.gguf) | Q5_K | 1.05GB |
+| [chinese-text-correction-1.5b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q5_K_M.gguf) | Q5_K_M | 1.05GB |
+| [chinese-text-correction-1.5b.Q5_1.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q5_1.gguf) | Q5_1 | 1.1GB |
+| [chinese-text-correction-1.5b.Q6_K.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q6_K.gguf) | Q6_K | 1.19GB |
+| [chinese-text-correction-1.5b.Q8_0.gguf](https://huggingface.co/RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf/blob/main/chinese-text-correction-1.5b.Q8_0.gguf) | Q8_0 | 1.53GB |
+
+
+
+
+Original model description:
+---
+library_name: transformers
+base_model: Qwen/Qwen2.5-1.5B-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。"
+---
+
+
+
+# Chinese Text Correction Model
+中文文本纠错模型chinese-text-correction-1.5b：用于拼写纠错、语法纠错
+
+`shibing624/chinese-text-correction-1.5b` 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-1.5b")
+
+    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-1.5b"
+
+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-1.5b
+|-- 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: 4
+- steps: 36000
+- eval_loss: 0.14
+- base model: Qwen/Qwen2.5-1.5B-Instruct
+- train data: [shibing624/chinese_text_correction](https://huggingface.co/datasets/shibing624/chinese_text_correction)
+- train time: 9 days 8 hours
+- eval_loss: ![](https://huggingface.co/shibing624/chinese-text-correction-1.5b-lora/resolve/main/eval_loss_1.5b.png)
+- train_loss: ![](https://huggingface.co/shibing624/chinese-text-correction-1.5b-lora/resolve/main/train_loss_1.5b.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},
+}
+```
+
+
+

chinese-text-correction-1.5b.IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6091fef362c3a5dac1c17cc8c4995ffdd3f1d21d98144d334de2d2448b557197
+size 941492256

chinese-text-correction-1.5b.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee3eb5a965f4ff2154c08ba75d2724a6db0294b5ef37912569ff1fe88ddee9c8
+size 902182944

chinese-text-correction-1.5b.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c697783924810134acf472c8954c1a755edbaa6718463455e09ceae686c0b338
+size 676304928

chinese-text-correction-1.5b.Q3_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd04623d68c186473d80d5a01a127f55e5d8db1c408bc60bc38e69922bea9181
+size 824178720

chinese-text-correction-1.5b.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b33ed6738703b43b0b83b5d2c94758e9bcdedade5deadbd4f0e86eb6f339f98
+size 880162848

chinese-text-correction-1.5b.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd04623d68c186473d80d5a01a127f55e5d8db1c408bc60bc38e69922bea9181
+size 824178720

chinese-text-correction-1.5b.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd27627d47c7caf2501baf02b305e5642abfa1b5391c673cde668dce9d346f9c
+size 760944672

chinese-text-correction-1.5b.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17743a891f3c2d52b329b6f0f05037fd6316c3a685e5f15a61ccd6c3aedcd44
+size 934955040

chinese-text-correction-1.5b.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63101f1b7a67e418f8cb6cae542e9a633977c7024539ddeaf3b66955b67b25ad
+size 1016842272

chinese-text-correction-1.5b.Q4_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4257b7df77f06ce6455e6a83f92c92c7e3b54a813270dfa0e8e41ab4b453046
+size 986048544

chinese-text-correction-1.5b.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4257b7df77f06ce6455e6a83f92c92c7e3b54a813270dfa0e8e41ab4b453046
+size 986048544

chinese-text-correction-1.5b.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fef9d1f6570076ab6b79e5f71461c205fef326873dd720927a967ffec674fa5
+size 940312608

chinese-text-correction-1.5b.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa169f8a7ba15a8c7bdc98f44c3c02d8cae739791e1200028263228bfc2ad8ce
+size 1098729504

chinese-text-correction-1.5b.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91011f919d0992b626b92f0fa795ac72def5a33ebb54003fdef599f3c32cf601
+size 1180616736

chinese-text-correction-1.5b.Q5_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9d8aa823a4fc24e29fbe442b02b54ab6fd423ee86cf3b011288eefbff9f9db
+size 1125050400

chinese-text-correction-1.5b.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9d8aa823a4fc24e29fbe442b02b54ab6fd423ee86cf3b011288eefbff9f9db
+size 1125050400

chinese-text-correction-1.5b.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5176b0c08f1432b791d5d67094d3d3f34f599d9736f1843e76289824812c8cca
+size 1098729504

chinese-text-correction-1.5b.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52832aeff788704cf145d0ac1e29d9414687b0f34e8d6c9c94440f3358a1ede
+size 1272739872

chinese-text-correction-1.5b.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e3fe8f659bfd4b5023dafefc9068a9daab3761bc2ebb5484d2ab7ff57382b1
+size 1646573088