LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Chinese Text Correction 7B by shibing624

 »  All LLMs  »  shibing624  »  Chinese Text Correction 7B   URL Share it on

  685   
  Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-7b-ins...   Conversational Dataset:shibing624/chinese tex...   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/shibing624/chinese-text-correction-7b 

Chinese Text Correction 7B Benchmarks

LLME Score: 0.25213
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Chinese Text Correction 7B (shibing624/chinese-text-correction-7b)

Chinese Text Correction 7B Parameters and Internals

Model Type 
text generation, text correction
Use Cases 
Areas:
text generation, spelling correction, grammatical error correction
Applications:
Chinese spelling and grammar error correction
Primary Use Cases:
text correction for spelling, grammar, audio similarity, visual similarity, and non-aligned length corrections
Additional Notes 
The model is integrated with the pycorrector library for ease of use in Chinese text correction tasks. Also available for use through HuggingFace Transformers.
Supported Languages 
zh (proficient)
Training Details 
Data Sources:
shibing624/chinese_text_correction
Training Time:
10 days
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
corrected text
Release Notes 
Version:
7b
Notes:
Release of a 7B parameter text correction model featuring high performance on Chinese Spelling Correction and Text Correction tasks.
LLM NameChinese Text Correction 7B
Repository 🤗https://huggingface.co/shibing624/chinese-text-correction-7b 
Base Model(s)  Qwen/Qwen2.5-7B-Instruct   Qwen/Qwen2.5-7B-Instruct
Model Size7b
Required VRAM15.2 GB
Updated2025-02-09
Maintainershibing624
Model Typeqwen2
Instruction-BasedYes
Model Files  10.0 GB: 1-of-2   5.2 GB: 2-of-2
Supported Languageszh
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Chinese Text Correction 7B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB36112192
Qwen2.5 7B RRP 1M986K / 15.2 GB1774
Qwen2.5 7B CelestialHarmony 1M986K / 14.8 GB584
COCO 7B Instruct 1M986K / 15.2 GB779
Q2.5 Instruct 1M Harmony986K / 15.2 GB381
Impish QWEN 7B 1M986K / 15.2 GB451
Qwen2.5 7B DeepSeek R1 1M986K / 15.2 GB708
MwM 7B CoT Merge1986K / 15.2 GB352
Mergekit Della Linear Vmeykci986K / 16.2 GB140
SJT 7B 1M986K / 15.2 GB171
Note: green Score (e.g. "73.2") means that the model is better than shibing624/chinese-text-correction-7b.

Rank the Chinese Text Correction 7B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 42848 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer