Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
objects76
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
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
main
zephyr-7b-dpo-qlora
/
runs
/
Apr05_17-15-39_gpu-1
/
events.out.tfevents.1712305026.gpu-1.1152924.0
Commit History
Model save
b8bf94d
verified
objects76
commited on
Apr 5
Training in progress, step 3500
666e963
verified
objects76
commited on
Apr 5
Training in progress, step 3400
3174726
verified
objects76
commited on
Apr 5
Training in progress, step 3300
7599f02
verified
objects76
commited on
Apr 5
Training in progress, step 3100
35259e7
verified
objects76
commited on
Apr 5
Training in progress, step 2900
593502a
verified
objects76
commited on
Apr 5
Training in progress, step 2800
dd724a9
verified
objects76
commited on
Apr 5
Training in progress, step 2600
571494a
verified
objects76
commited on
Apr 5
Training in progress, step 2300
bb9e085
verified
objects76
commited on
Apr 5
Training in progress, step 2100
f3dcbd2
verified
objects76
commited on
Apr 5
Training in progress, step 1500
d73eed1
verified
objects76
commited on
Apr 5
Training in progress, step 1000
a189686
verified
objects76
commited on
Apr 5
Training in progress, step 800
659dfcf
verified
objects76
commited on
Apr 5
Training in progress, step 600
70b53b0
verified
objects76
commited on
Apr 5
Training in progress, step 400
13990f9
verified
objects76
commited on
Apr 5