Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
lamm-mit
/
mistral-7B-v0.3-Instruct-CPT_SFT-DPO
like
0
Follow
LAMM: MIT Laboratory for Atomistic and Molecular Mechanics
37
Text Generation
Transformers
TensorBoard
Safetensors
lamm-mit/orpo-dpo-mix-40k
lamm-mit/bio-inspired-DPO
lamm-mit/spider-silk-DPO
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
main
mistral-7B-v0.3-Instruct-CPT_SFT-DPO
/
tokenizer_config.json
Commit History
Training in progress, epoch 1
2a07250
verified
mjbuehler
commited on
Aug 27