Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
gabrielmbmb
/
smollm2-1.7B-8k-mix7-ep2-v2-qlora-r16-a16-lr3e4-mix1-dpo
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
llama
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
ab610d7
smollm2-1.7B-8k-mix7-ep2-v2-qlora-r16-a16-lr3e4-mix1-dpo
/
runs
/
Nov05_11-27-51_ip-26-0-167-175
/
events.out.tfevents.1730808720.ip-26-0-167-175.3215185.1
Commit History
End of training
ab610d7
verified
gabrielmbmb
HF staff
commited on
27 days ago