Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
martimfasantos
/
tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_adamw_3epochs
like
0
Text Generation
Transformers
TensorBoard
Safetensors
haoranxu/ALMA-R-Preference
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
44811ff
tinyllama-1.1b-mt-dpo-full_LR5e-8_BS16_adamw_3epochs
/
runs
/
Jul09_21-21-38_poseidon
1 contributor
History:
17 commits
martimfasantos
Training in progress, step 4100
44811ff
verified
6 months ago
events.out.tfevents.1720560144.poseidon.534326.0
288 kB
LFS
Training in progress, step 4100
6 months ago