Octogeex by bigcode

 ยป  All LLMs  ยป  bigcode  ยป  Octogeex   URL Share it on

  Arxiv:2308.07124   Chatglm   Codegeex   Custom code   Dataset:bigcode/commitpackft   Dataset:bigcode/oasst-octopack   En   Endpoints compatible   Glm   Model-index   Pytorch   Region:us   Zh
Model Card on HF ๐Ÿค—: https://huggingface.co/bigcode/octogeex 

Octogeex Benchmarks

Octogeex (bigcode/octogeex)

Octogeex Parameters and Internals

Model Type 
text-generation, code-writing
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
instruction following in code generation
Limitations:
known limitations or unsuitable use cases not specified
Training Details 
Data Sources:
CommitPackFT, OASST
Data Volume:
1 trillion pretraining & 2M instruction tuning tokens
Methodology:
instruction tuning
Training Time:
24 days
Hardware Used:
512 Tesla A100 GPUs
Model Architecture:
GPT-2 model with multi-query attention and Fill-in-the-Middle objective
Input Output 
Input Format:
Instructions prefixed with 'Question: ' and suffixed with 'Answer:'
Accepted Modalities:
text
Output Format:
Text generated for code tasks.
Performance Tips:
Preface input with correct format for optimal results.
LLM NameOctogeex
Repository ๐Ÿค—https://huggingface.co/bigcode/octogeex 
Model Size6b
Required VRAM12.5 GB
Updated2025-02-05
Maintainerbigcode
Model Typechatglm
Model Files  12.5 GB
Supported Languageszh en
Model ArchitectureChatGLMModel
Transformers Version4.30.2
Tokenizer ClassChatGLMTokenizer
Torch Data Typebfloat16

Best Alternatives to Octogeex

Best Alternatives
Context / RAM
Downloads
Likes
Chatglm2 6B0K / 12.5 GB6856782038
Chatglm3 6B0K / 12.5 GB304621105
Chatglm 6B0K / 13.5 GB86632850
Codegeex2 6B0K / 12.5 GB168253
Note: green Score (e.g. "73.2") means that the model is better than bigcode/octogeex.

Rank the Octogeex Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 42577 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227