Hugging Face's logo

just1nseo
/
zephyr-dpo-qlora-gpt4-5e-7-epoch3

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
zephyr-dpo-qlora-gpt4-5e-7-epoch3

Commit History

Model save
6d917ec
verified

just1nseo commited on

Training in progress, step 1000
06a2b7d
verified

just1nseo commited on

Training in progress, step 900
b32c0f2
verified

just1nseo commited on

Training in progress, step 800
7d57f14
verified

just1nseo commited on

Training in progress, step 700
ef9a075
verified

just1nseo commited on

Training in progress, step 600
1fe274e
verified

just1nseo commited on

Training in progress, step 500
403d7df
verified

just1nseo commited on

Training in progress, step 400
0eb2e65
verified

just1nseo commited on

Training in progress, step 300
f2da129
verified

just1nseo commited on

Training in progress, step 200
e2d22e2
verified

just1nseo commited on

Training in progress, step 100
9267f90
verified

just1nseo commited on

initial commit
71e056c
verified

just1nseo commited on