Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
prosecalign
/
clm7b0129-kendall-onof-ofif-corr-max-2-simpo-max1500-decay-sft-beta1.5-gamma0.5-lr5e-6
like
0
Follow
Proactive Security Alignment
6
Transformers
Safetensors
Generated from Trainer
llama-factory
arxiv:
2305.18290
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
dd7dc9a
clm7b0129-kendall-onof-ofif-corr-max-2-simpo-max1500-decay-sft-beta1.5-gamma0.5-lr5e-6
/
trainer_log.jsonl
Commit History
Training in progress, step 300
dd7dc9a
verified
ziansu
commited on
Jan 30
Training in progress, step 250
81ccf68
verified
ziansu
commited on
Jan 30
Training in progress, step 200
eea4a3f
verified
ziansu
commited on
Jan 30
Training in progress, step 150
db4b780
verified
ziansu
commited on
Jan 30
Training in progress, step 100
5d41b25
verified
ziansu
commited on
Jan 30
Training in progress, step 50
192876e
verified
ziansu
commited on
Jan 30