Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ilharco
/
altruistic-zephyr-7b-sft-qlora
like
0
PEFT
TensorBoard
Safetensors
ilharco/altruism_1k
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
df97976
altruistic-zephyr-7b-sft-qlora
/
runs
/
Feb12_23-07-01_debian
1 contributor
History:
2 commits
ilharco
Model save
df97976
verified
8 months ago
events.out.tfevents.1707775659.debian.74814.0
Safe
18.6 kB
LFS
Model save
8 months ago
events.out.tfevents.1707777120.debian.74814.1
Safe
828 Bytes
LFS
Model save
8 months ago