Hugging Face's logo

sfulay
/
zephyr-7b-dpo-full-gpt_consistent-reward-scale-05

Safetensors
mistral
trl
dpo
Generated from Trainer
Model card Files Community
zephyr-7b-dpo-full-gpt_consistent-reward-scale-05

Commit History

Model save
afd7314
verified

sfulay commited on

Training in progress, step 436
a4b7e39
verified

sfulay commited on

Training in progress, step 400
1501126
verified

sfulay commited on

Training in progress, step 300
fc2c415
verified

sfulay commited on

Training in progress, step 200
3394f33
verified

sfulay commited on

Training in progress, step 100
251193f
verified

sfulay commited on

Training in progress, step 100
4574324
verified

sfulay commited on

initial commit
0c3d28e
verified

sfulay commited on