Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Corianas
/
Llama-3-Instruct-8B-SPPO-Iter3-8-32-GPTQ
like
0
Text Generation
Safetensors
openbmb/UltraFeedback
English
llama
autoquant
UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
gptq
conversational
Eval Results
8-bit precision
arxiv:
2405.00675
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
d47c40e
Llama-3-Instruct-8B-SPPO-Iter3-8-32-GPTQ
/
model.safetensors.index.json
Commit History
Upload folder using huggingface_hub
d47c40e
verified
Corianas
commited on
Aug 24