Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
martimfasantos
/
tinyllama-1.1b-mt-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
haoranxu/ALMA-R-Preference
llama
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
33e4f6e
tinyllama-1.1b-mt-dpo-qlora
1 contributor
History:
1 commit
martimfasantos
initial commit
33e4f6e
verified
5 months ago
.gitattributes
Safe
1.52 kB
initial commit
5 months ago