Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
David-Xu
/
cira-7b-dpo-lora-merge
like
0
PEFT
TensorBoard
Safetensors
David-Xu/astronomy-stack-dpo-20-percent
llama
alignment-handbook
Generated from Trainer
4-bit precision
bitsandbytes
License:
mit
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
8c76de3
cira-7b-dpo-lora-merge
/
runs
/
Mar11_07-47-23_b89f062cf3e1
1 contributor
History:
9 commits
David-Xu
Training in progress, step 900
89bd182
verified
8 months ago
events.out.tfevents.1710143296.b89f062cf3e1.43461.0
Safe
68.2 kB
LFS
Training in progress, step 900
8 months ago
events.out.tfevents.1710148786.b89f062cf3e1.43461.1
Safe
828 Bytes
LFS
Training in progress, step 900
8 months ago