Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ale-bay
/
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
452055b
zephyr-7b-dpo-qlora
/
runs
/
Mar07_10-30-46_ale-dpo-2-0-0
/
events.out.tfevents.1709807802.ale-dpo-2-0-0.1134.0
Commit History
Training in progress, step 1900
b84a28f
verified
ale-bay
commited on
Mar 7
Training in progress, step 1800
9fda776
verified
ale-bay
commited on
Mar 7
Training in progress, step 1700
d02fd4f
verified
ale-bay
commited on
Mar 7
Training in progress, step 1500
2f85f6d
verified
ale-bay
commited on
Mar 7
Training in progress, step 1400
24000eb
verified
ale-bay
commited on
Mar 7
Training in progress, step 1300
bff66aa
verified
ale-bay
commited on
Mar 7
Training in progress, step 1200
3a70178
verified
ale-bay
commited on
Mar 7
Training in progress, step 1100
2ba6a2c
verified
ale-bay
commited on
Mar 7
Training in progress, step 1000
11de811
verified
ale-bay
commited on
Mar 7
Training in progress, step 900
4ccac30
verified
ale-bay
commited on
Mar 7
Training in progress, step 800
b9ad63e
verified
ale-bay
commited on
Mar 7
Training in progress, step 700
eebd539
verified
ale-bay
commited on
Mar 7
Training in progress, step 600
a25719a
verified
ale-bay
commited on
Mar 7
Training in progress, step 500
3fda64b
verified
ale-bay
commited on
Mar 7
Training in progress, step 400
77e0b4e
verified
ale-bay
commited on
Mar 7
Training in progress, step 300
5d846f2
verified
ale-bay
commited on
Mar 7
Training in progress, step 200
3e5e20a
verified
ale-bay
commited on
Mar 7
Training in progress, step 100
4a4a31e
verified
ale-bay
commited on
Mar 7