YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

lora_compTrue_seed0

Adapter weights (LORA) for gpt2, fine-tuned on SST-2 and evaluated for transfer to Rotten Tomatoes.

Trainable params: 1,181,186 / 125,620,994 (0.9403%)

SST-2 val acc: 0.9174
Rotten Tomatoes few-shot transfer acc: 0.8696

Part of the KoRA project. Load adapter.pt as a state_dict subset onto the corresponding model class in kora_lm_experiment.py.

Downloads last month
14
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support