Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
silviasapora
/
mistral-7b-borpo-noisy-5e-5-01-norm2
like
0
Text Generation
Transformers
TensorBoard
Safetensors
silviasapora/dpo_7k_noisy_10
mistral
Generated from Trainer
alignment-handbook
trl
orpo
conversational
text-generation-inference
Inference Endpoints
arxiv:
2403.07691
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
a2a488a
mistral-7b-borpo-noisy-5e-5-01-norm2
Commit History
Model save
a2a488a
verified
silviasapora
commited on
11 days ago
Training in progress, step 315
7431a6c
verified
silviasapora
commited on
11 days ago
initial commit
af3a58a
verified
silviasapora
commited on
11 days ago