Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
cyberpole
/
Mistral-7B-Instruct-v0.2-mergedORPO-r8
like
0
Follow
Cyber-pôle des révolutionnaires
4
PEFT
TensorBoard
Safetensors
trl
orpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
1366b83
Mistral-7B-Instruct-v0.2-mergedORPO-r8
/
runs
/
Aug22_17-48-01_aaceca5f107c
1 contributor
History:
7 commits
k-r-l
Training in progress, step 28
d34ff8d
verified
3 months ago
events.out.tfevents.1724348888.aaceca5f107c.1822.0
Safe
29.4 kB
LFS
Training in progress, step 28
3 months ago