Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
just1nseo
/
zephyr-dpo-qlora-gpt4-5e-6-epoch3
like
0
PEFT
TensorBoard
Safetensors
generation/GPT4
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
6f4d452
zephyr-dpo-qlora-gpt4-5e-6-epoch3
Commit History
Model save
6f4d452
verified
just1nseo
commited on
Jul 29
Training in progress, step 1000
7d77b52
verified
just1nseo
commited on
Jul 29
Training in progress, step 900
f544b0f
verified
just1nseo
commited on
Jul 29
Training in progress, step 800
f78ea69
verified
just1nseo
commited on
Jul 29
Training in progress, step 700
77c89e7
verified
just1nseo
commited on
Jul 29
Training in progress, step 600
7d35c83
verified
just1nseo
commited on
Jul 29
Training in progress, step 500
1149528
verified
just1nseo
commited on
Jul 29
Training in progress, step 400
6c2f814
verified
just1nseo
commited on
Jul 29
Training in progress, step 300
9d30451
verified
just1nseo
commited on
Jul 29
Training in progress, step 200
60d0f07
verified
just1nseo
commited on
Jul 29
initial commit
b835b60
verified
just1nseo
commited on
Jul 29