Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
EllieS
/
zephyr-7b-dpo-lora-pubmedqa-mix2
like
0
PEFT
TensorBoard
Safetensors
EllieS/pubmedqa_dpo_mix_data
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
8614683
zephyr-7b-dpo-lora-pubmedqa-mix2
/
runs
/
Mar03_06-19-23_586cb8b6da8c
1 contributor
History:
84 commits
EllieS
Model save
8f17533
verified
8 months ago
events.out.tfevents.1709446868.586cb8b6da8c.24054.0
Safe
5.4 MB
LFS
Model save
8 months ago
events.out.tfevents.1709583061.586cb8b6da8c.24054.1
Safe
841 Bytes
LFS
Model save
8 months ago