Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
dmariko
/
SmolLM-1.7B-Instruct-dpo-16k
like
0
TensorBoard
Safetensors
English
llama
trl
dpo
Generated from Trainer
License:
cc-by-nc-4.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
main
SmolLM-1.7B-Instruct-dpo-16k
/
runs
/
Sep16_04-20-31_ip-172-16-3-91.eu-west-1.compute.internal
1 contributor
History:
7 commits
dmariko
Training in progress, epoch 6
7930469
verified
about 1 month ago
events.out.tfevents.1726460500.ip-172-16-3-91.eu-west-1.compute.internal.47601.0
Safe
15.1 kB
LFS
Training in progress, epoch 6
about 1 month ago