Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Flowersea37
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
qwen2
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
5d3b3cd
zephyr-7b-dpo-qlora
/
adapter_model.safetensors
Commit History
Training in progress, step 2547
5d3b3cd
verified
Flowersea37
commited on
Sep 26
Training in progress, step 2500
f9e043a
verified
Flowersea37
commited on
Sep 26
Training in progress, step 2300
3298f7a
verified
Flowersea37
commited on
Sep 26
Training in progress, step 2200
31a31d7
verified
Flowersea37
commited on
Sep 26
Training in progress, step 2000
f816108
verified
Flowersea37
commited on
Sep 26
Training in progress, step 1900
4ecbf54
verified
Flowersea37
commited on
Sep 26
Training in progress, step 1800
97950ae
verified
Flowersea37
commited on
Sep 26
Training in progress, step 1600
6d3e685
verified
Flowersea37
commited on
Sep 26
Training in progress, step 1300
bbc2ded
verified
Flowersea37
commited on
Sep 26
Training in progress, step 1000
63e13ec
verified
Flowersea37
commited on
Sep 26
Training in progress, step 800
960d295
verified
Flowersea37
commited on
Sep 26
Training in progress, step 700
054309f
verified
Flowersea37
commited on
Sep 26
Training in progress, step 600
116ba79
verified
Flowersea37
commited on
Sep 26
Training in progress, step 500
2144593
verified
Flowersea37
commited on
Sep 26
Training in progress, step 400
10c8f87
verified
Flowersea37
commited on
Sep 26
Training in progress, step 300
6596cb7
verified
Flowersea37
commited on
Sep 26
Training in progress, step 100
1f26760
verified
Flowersea37
commited on
Sep 26