Hugging Face's logo

dball
/
zephyr-7b-dpo-qlora-no-sft

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
Model card Files Metrics Community
1
zephyr-7b-dpo-qlora-no-sft

Commit History

Training in progress, step 2500
fa67542
verified

dball commited on

Training in progress, step 2400
9bbf8df
verified

dball commited on

Training in progress, step 2300
4bbb89d
verified

dball commited on

Training in progress, step 2200
30bc5dd
verified

dball commited on

Training in progress, step 2100
e23e7ef
verified

dball commited on

Training in progress, step 2000
42d29c0
verified

dball commited on

Training in progress, step 1900
bf94f6b
verified

dball commited on

Training in progress, step 1800
0ec1bf1
verified

dball commited on

Training in progress, step 1700
289318a
verified

dball commited on

Training in progress, step 1600
3113ac6
verified

dball commited on

Training in progress, step 1500
e6a1c9f
verified

dball commited on

Training in progress, step 1400
db38aa4
verified

dball commited on

Training in progress, step 1300
db910a3
verified

dball commited on

Training in progress, step 1200
622dcda
verified

dball commited on

Training in progress, step 1100
72d995f
verified

dball commited on

Training in progress, step 1000
7db0212
verified

dball commited on

Training in progress, step 900
2619608
verified

dball commited on

Training in progress, step 800
37fcd01
verified

dball commited on

Training in progress, step 700
9a2ee45
verified

dball commited on

Training in progress, step 600
ce3867a
verified

dball commited on

Training in progress, step 500
bf49c75
verified

dball commited on

Training in progress, step 300
1b8a31f
verified

dball commited on

Training in progress, step 200
a8d6cf5
verified

dball commited on

initial commit
a2630d6
verified

dball commited on