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

Codegeex2 6B by THUDM

 »  All LLMs  »  THUDM  »  Codegeex2 6B   URL Share it on

  119   

Codegeex2 6B is an open-source language model by THUDM. Features: 6b LLM, VRAM: 12.5GB, LLM Explorer Score: 0.1, HumanEval: 33.5.

  Arxiv:2303.17568   Chatglm   Codegeex   Custom code   En   Endpoints compatible   Glm   Pytorch   Region:us   Sharded   Thudm   Zh
Model Card on HF 🤗: https://huggingface.co/THUDM/codegeex2-6b 

Codegeex2 6B Benchmarks

HumanEvalA: 21.23
Python Eva: 33.49 vs 92 (so35)-63.6%
Java Eval: 23.46
Javascript: 29.9
CPP Eval: 28.45
PHP Eval: 25.27
Julia Eval: 20.93
D Eval: 8.44
Lua Eval: 15.94
R Eval: 14.58
Racket Eva: 11.75
Rust Eval: 20.45
Swift Eval: 22.06
LLME Score: 0.09558
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Codegeex2 6B (THUDM/codegeex2-6b)
🌟 Advertise your project 🚀

Codegeex2 6B Parameters and Internals

Model Type 
Multilingual Code Generation
Use Cases 
Areas:
Research, Commercial Applications
Applications:
Coding assistants, Code generation, Code translation
Primary Use Cases:
Code generation in various languages, Automated code completion, AI-assisted programming
Limitations:
Advised against use in critical code deployments without review
Additional Notes 
CodeGeeX2 significantly improves over the first generation, adding more powerful features and multilingual support.
Supported Languages 
zh (Chinese), en (English)
Training Details 
Data Sources:
Various code sources for pre-training
Data Volume:
600B code tokens
Methodology:
Based on ChatGLM2 architecture.
Context Length:
8192
Model Architecture:
ChatGLM2 with additional code pre-training
Input Output 
Input Format:
Language tagged code prompts
Accepted Modalities:
Textual code inputs
Output Format:
Generated code
Performance Tips:
Adding language tags to prompts can improve performance.
LLM NameCodegeex2 6B
Repository 🤗https://huggingface.co/THUDM/codegeex2-6b 
Model Size6b
Required VRAM12.5 GB
Updated2025-07-28
MaintainerTHUDM
Model Typechatglm
Model Files  1.8 GB: 1-of-7   2.0 GB: 2-of-7   1.9 GB: 3-of-7   1.8 GB: 4-of-7   2.0 GB: 5-of-7   1.9 GB: 6-of-7   1.1 GB: 7-of-7
Supported Languageszh en
Model ArchitectureChatGLMModel
Transformers Version4.30.2
Tokenizer ClassChatGLMTokenizer
Torch Data Typebfloat16

Best Alternatives to Codegeex2 6B

Best Alternatives
Context / RAM
Downloads
Likes
Chatglm3 6B0K / 12.5 GB6591541138
Chatglm2 6B0K / 12.5 GB4939922058
Chatglm3 6B0K / 12.5 GB1866511163
Chatglm2 6B0K / 12.5 GB6173252050
Chatglm 6B0K / 13.5 GB75252887
Chatglm 6B0K / 13.5 GB28162862
Codegeex2 6B0K / 12.5 GB131258
Octogeex0K / 12.5 GB80723
Note: green Score (e.g. "73.2") means that the model is better than THUDM/codegeex2-6b.

Rank the Codegeex2 6B 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? 53972 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