Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
martimfasantos
/
tinyllama-1.1b-sum-dpo-full_LR1e-7_2epochs
like
0
Text Generation
Transformers
TensorBoard
Safetensors
openai/summarize_from_feedback
llama
alignment-handbook
trl
dpo
Generated from Trainer
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
6ccdf96
tinyllama-1.1b-sum-dpo-full_LR1e-7_2epochs
/
runs
/
May15_16-59-39_poseidon
1 contributor
History:
118 commits
martimfasantos
End of training
cf3b440
verified
6 months ago
events.out.tfevents.1715792891.poseidon.3676190.0
Safe
890 kB
LFS
Model save
6 months ago
events.out.tfevents.1715882392.poseidon.3676190.1
Safe
828 Bytes
LFS
End of training
6 months ago