Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
jikaixuan
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
1b1d13d
zephyr-7b-dpo-qlora
/
adapter_model.safetensors
Commit History
Model save
49b9b9f
verified
jikaixuan
commited on
Feb 19
Training in progress, step 400
f7c95fc
verified
jikaixuan
commited on
Feb 19
Training in progress, step 400
3bfa5b1
verified
jikaixuan
commited on
Feb 19
Training in progress, step 300
937bdfb
verified
jikaixuan
commited on
Feb 19
Training in progress, step 200
90d7786
verified
jikaixuan
commited on
Feb 19
Model save
6366e7e
verified
jikaixuan
commited on
Jan 15
Training in progress, step 900
251136a
verified
jikaixuan
commited on
Jan 15
Training in progress, step 800
070e197
verified
jikaixuan
commited on
Jan 15
Training in progress, step 700
c1d0324
verified
jikaixuan
commited on
Jan 15
Training in progress, step 600
4a734ac
verified
jikaixuan
commited on
Jan 15
Training in progress, step 500
6c81b1b
verified
jikaixuan
commited on
Jan 15
Training in progress, step 400
6800838
verified
jikaixuan
commited on
Jan 15
Training in progress, step 300
8744dad
verified
jikaixuan
commited on
Jan 15
Training in progress, step 200
d726c0e
verified
jikaixuan
commited on
Jan 15
Training in progress, step 100
834ad57
verified
jikaixuan
commited on
Jan 15
Training in progress, step 100
04ab470
verified
jikaixuan
commited on
Jan 14
jikaixuan
commited on
