Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
sanduntg
/
output
like
0
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
Model card
Files
Files and versions
Metrics
Training metrics
Community
main
output
/
runs
1 contributor
History:
2 commits
sanduntg
sanduntg/llama_2_dpo_with_reward_1000
27e25fd
verified
10 months ago
Mar15_16-16-42_e083a9d2908e
sanduntg/llama_2_dpo_with_reward_2
11 months ago
Mar20_16-41-22_d12c3011894c
sanduntg/llama_2_dpo_with_reward_1000
10 months ago