hugpadhugpad

SentientAGI / Dobby-Unhinged-Llama-3.3-70B_GGUF

Other1156Updated Feb 12, 2025
Hugging Face

Downloads

115

Likes

6

Last updated

Feb 12, 2025

License

llama3.3

Dobby-70B high-performance GGUF model based on Llama 3.3 with 70 billion parameters. Designed for efficiency, this model supports quantization levels in 4-bit, 6-bit, and 8-bit, offering flexibility to run on various hardware configurations without compromising performance.

Tasks & library

  • transformers

Tags

  • transformers
  • gguf
  • Llama-3.3
  • Instruct
  • loyal AI
  • GGUF

Technical specifications

ParametersNot available
Librarytransformers
Languagesen
Base modelmeta-llama/Llama-3.3-70B-Instruct
Licensellama3.3