richarderkhov/shibing624_-_chinese-text-correction-1.5b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://huggingface.co/shibing624/chinese-text-correction-1.5b-lora/resolve/main/eval_loss_1.5b.png",
    "summary": "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  | | chinese-text-correction-1.5b-lora  |  Qwen/Qwen2.5-1.5B-Instruct             | 🤗 Hugging Face  | | chinese-text-correction-7b   |  Qwen/Qwen2.5-7B-Instruct             | 🤗 Hugging Face  | | chinese-text-correction-7b-lora  |  Qwen/Qwen2.5-7B-Instruct             | 🤗 Hugging Face  | ### 评估结果 | Model Name       | Model Link                                                                                                              | Base Model                 | Avg        | SIGHAN-2015 | EC-LAW | MCSC   | GPU/CPU | QPS     | |:-----------------|:------------------------------------------------------------------------------------------------------------------------|:---------------------------|:-----------|:------------|:-------|:-------|:--------|:--------| | Kenlm-CSC        | shibing624/chinese-kenlm-klm                                     | kenlm | 0.3409     | 0.3147      | 0.3763 | 0.3317 | CPU     | 9       | | Mengzi-T5-CSC    | shibing624/mengzi-t5-base-chinese-correction     | mengzi-t5-base | 0.3984     | 0.7758      | 0.3156 | 0.1039 | GPU     | 214     | | ERNIE-CSC        | PaddleNLP/ernie-csc | PaddlePaddle/ernie-1.0-base-zh | 0.4353     | 0.8383      | 0.3357 | 0.1318 | GPU     | 114     | | MacBERT-CSC      | 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               | THUDM/chatglm3-6b          | 0.4538     | 0.6572      | 0.4369     | 0.2672      | GPU     | 3       | | Qwen2.5-1.5B-CTC | 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                   | Qwen/Qwen2.5-7B-Instruct   | **0.8225** | 0.4917      | 0.9798 | 0.9959 | GPU     | 3       |",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nchinese-text-correction-1.5b - GGUF\n- Model creator: https://huggingface.co/shibing624/\n- Original model: https://huggingface.co/shibing624/chinese-text-correction-1.5b/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n| [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 |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nbase_model: Qwen/Qwen2.5-1.5B-Instruct\nlicense: apache-2.0\ndatasets:\n- shibing624/chinese_text_correction\nlanguage:\n- zh\nmetrics:\n- f1\ntags:\n- text-generation-inference\nwidget:\n- text: \"文本纠错：\\n少先队员因该为老人让坐。\"\n---\n\n\n\n# Chinese Text Correction Model\n中文文本纠错模型chinese-text-correction-1.5b：用于拼写纠错、语法纠错\n\n`shibing624/chinese-text-correction-1.5b` evaluate test data：\n\nThe overall performance of CSC **test**:\n\n|input_text|predict_text|\n|:--- |:--- |\n|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。|\n\n# Models\n\n| Name            |  Base Model   | Download                        |\n|-----------------|-------------------|-----------------------------------------------------------------------|\n| chinese-text-correction-1.5b  |  Qwen/Qwen2.5-1.5B-Instruct             | [🤗 Hugging Face](https://huggingface.co/shibing624/chinese-text-correction-1.5b)  |\n| chinese-text-correction-1.5b-lora  |  Qwen/Qwen2.5-1.5B-Instruct             | [🤗 Hugging Face](https://huggingface.co/shibing624/chinese-text-correction-1.5b-lora)  |\n| chinese-text-correction-7b   |  Qwen/Qwen2.5-7B-Instruct             | [🤗 Hugging Face](https://huggingface.co/shibing624/chinese-text-correction-7b)  |\n| chinese-text-correction-7b-lora  |  Qwen/Qwen2.5-7B-Instruct             | [🤗 Hugging Face](https://huggingface.co/shibing624/chinese-text-correction-7b-lora)  |\n\n\n### 评估结果\n- 评估指标：F1\n- 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\n- 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\n- GPU：Tesla V100，显存 32 GB\n\n| Model Name       | Model Link                                                                                                              | Base Model                 | Avg        | SIGHAN-2015 | EC-LAW | MCSC   | GPU/CPU | QPS     |\n|:-----------------|:------------------------------------------------------------------------------------------------------------------------|:---------------------------|:-----------|:------------|:-------|:-------|:--------|:--------|\n| Kenlm-CSC        | [shibing624/chinese-kenlm-klm](https://huggingface.co/shibing624/chinese-kenlm-klm)                                     | kenlm | 0.3409     | 0.3147      | 0.3763 | 0.3317 | CPU     | 9       |\n| 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     |\n| 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     |\n| 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** |\n| 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       |\n| 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       |\n| 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       |\n\n## Usage (pycorrector)\n\n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：\n\nInstall package:\n```shell\npip install -U pycorrector\n```\n\n```python\nfrom pycorrector.gpt.gpt_corrector import GptCorrector\n\nif __name__ == '__main__':\n    error_sentences = [\n        '真麻烦你了。希望你们好好的跳无',\n        '少先队员因该为老人让坐',\n        '机七学习是人工智能领遇最能体现智能的一个分知',\n        '一只小鱼船浮在平净的河面上',\n        '我的家乡是有明的渔米之乡',\n    ]\n    m = GptCorrector(\"shibing624/chinese-text-correction-1.5b\")\n\n    batch_res = m.correct_batch(error_sentences)\n    for i in batch_res:\n        print(i)\n        print()\n```\n\n## Usage (HuggingFace Transformers)\nWithout [pycorrector](https://github.com/shibing624/pycorrector), you can use the model like this: \n\nFirst, you pass your input through the transformer model, then you get the generated sentence.\n\nInstall package:\n```\npip install transformers \n```\n\n```python\n# pip install transformers\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\ncheckpoint = \"shibing624/chinese-text-correction-1.5b\"\n\ndevice = \"cuda\" # for GPU usage or \"cpu\" for CPU usage\ntokenizer = AutoTokenizer.from_pretrained(checkpoint)\nmodel = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)\n\ninput_content = \"文本纠错：\\n少先队员因该为老人让坐。\"\n\nmessages = [{\"role\": \"user\", \"content\": input_content}]\ninput_text=tokenizer.apply_chat_template(messages, tokenize=False)\n\nprint(input_text)\n\ninputs = tokenizer.encode(input_text, return_tensors=\"pt\").to(device)\noutputs = model.generate(inputs, max_new_tokens=1024, temperature=0, do_sample=False, repetition_penalty=1.08)\n\nprint(tokenizer.decode(outputs[0]))\n```\n\noutput:\n```shell\n少先队员应该为老人让座。\n```\n\n\n模型文件组成：\n```\nshibing624/chinese-text-correction-1.5b\n|-- added_tokens.json\n|-- config.json\n|-- generation_config.json\n|-- merges.txt\n|-- model.safetensors\n|-- model.safetensors.index.json\n|-- README.md\n|-- special_tokens_map.json\n|-- tokenizer_config.json\n|-- tokenizer.json\n`-- vocab.json\n```\n\n#### 训练参数：\n\n- num_epochs: 8\n- batch_size: 4\n- steps: 36000\n- eval_loss: 0.14\n- base model: Qwen/Qwen2.5-1.5B-Instruct\n- train data: [shibing624/chinese_text_correction](https://huggingface.co/datasets/shibing624/chinese_text_correction)\n- train time: 9 days 8 hours\n- eval_loss: ![](https://huggingface.co/shibing624/chinese-text-correction-1.5b-lora/resolve/main/eval_loss_1.5b.png)\n- train_loss: ![](https://huggingface.co/shibing624/chinese-text-correction-1.5b-lora/resolve/main/train_loss_1.5b.png)\n\n### 训练数据集\n#### 中文纠错数据集\n\n- 数据：[shibing624/chinese_text_correction](https://huggingface.co/datasets/shibing624/chinese_text_correction)\n\n\n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)\n\n## Citation\n\n```latex\n@software{pycorrector,\n  author = {Xu Ming},\n  title = {pycorrector: Implementation of language model finetune},\n  year = {2024},\n  url = {https://github.com/shibing624/pycorrector},\n}\n```\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 286,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-27T19:52:03.000Z",
  "created_at": "2024-10-27T18:18:30.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "671e83f65c3da2e7b50c76a2",
  "id": "RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf",
  "modelId": "RichardErkhov/shibing624_-_chinese-text-correction-1.5b-gguf",
  "sha": "28f0d26916b7ac5fe7a1e9101bbe97e215b461f6",
  "createdAt": "2024-10-27T18:18:30.000Z",
  "lastModified": "2024-10-27T19:52:03.000Z",
  "author": "RichardErkhov",
  "downloads": 286,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}