Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
chaoweihuang
/
FactAlign-LLaMA-3-8B
like
1
Text Generation
Transformers
TensorBoard
Safetensors
trl-lib/kto-mix-14k
chaoweihuang/lf-response-llama3-f1_100_0.8-fg0.5
llama
alignment-handbook
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
arxiv:
2410.01691
License:
llama3
Model card
Files
Files and versions
Metrics
Training metrics
Community
1
Train
Deploy
Use this model
main
FactAlign-LLaMA-3-8B
/
train_results.json
Commit History
Upload folder using huggingface_hub
eae09c2
verified
chaoweihuang
commited on
Jul 29
chaoweihuang
commited on
