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

Chinese Text Correction 1.5B by shibing624

 »  All LLMs  »  shibing624  »  Chinese Text Correction 1.5B   URL Share it on

  608   

Chinese Text Correction 1.5B is an open-source language model by shibing624. Features: 1.5b LLM, VRAM: 3.1GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.17.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-1.5b-i...   Conversational Dataset:shibing624/chinese tex...   Deploy:azure   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/shibing624/chinese-text-correction-1.5b 

Chinese Text Correction 1.5B Benchmarks

LLME Score: 0.17167
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 1.5B (shibing624/chinese-text-correction-1.5b)
🌟 Advertise your project 🚀

Chinese Text Correction 1.5B Parameters and Internals

Model Type 
text correction
Use Cases 
Areas:
spelling correction, grammar correction
Primary Use Cases:
Chinese Text Correction (CTC), Chinese Spelling Correction (CSC)
Additional Notes 
The model is part of the pycorrector project and can be used with or without it.
Supported Languages 
zh (proficient)
Training Details 
Data Sources:
shibing624/chinese_text_correction
Training Time:
9 days 8 hours
Hardware Used:
Tesla V100, 32 GB VRAM
Input Output 
Input Format:
text input through encoder
Accepted Modalities:
text
Output Format:
corrected text output
LLM NameChinese Text Correction 1.5B
Repository 🤗https://huggingface.co/shibing624/chinese-text-correction-1.5b 
Base Model(s)  Qwen/Qwen2.5-1.5B-Instruct   Qwen/Qwen2.5-1.5B-Instruct
Model Size1.5b
Required VRAM3.1 GB
Updated2026-04-10
Maintainershibing624
Model Typeqwen2
Instruction-BasedYes
Model Files  3.1 GB
Supported Languageszh
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Chinese Text Correction 1.5B

Best Alternatives
Context / RAM
Downloads
Likes
AceInstruct 1.5B128K / 3.5 GB7688020
Gte Qwen2 1.5B Instruct128K / 7.1 GB287910229
... Abliterated TIES Qwen2.5 1.5B128K / 3.5 GB50
Saba1 1.8B128K / 3.6 GB131
Miniclaus Qw1.5B UNAMGS128K / 3.5 GB88
Bellatrix 1.5B XElite128K / 3.5 GB93
GCIRS Reasoning 1.5B R1128K / 3.5 GB201
...illed Scout 1.5B Instruct Gen1128K / 3.5 GB60
Deepthink 1.5B Open PRM128K / 7.1 GB60
...pmath Competitive 1.5B Preview128K / 7.1 GB60
Note: green Score (e.g. "73.2") means that the model is better than shibing624/chinese-text-correction-1.5b.

Rank the Chinese Text Correction 1.5B 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer