Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
kora-gpt2-sst2-lora_compTrue_seed0 – AI Model by OnePunchMonk101010 | AlphaNeural AI
You can deploy this model and start earning money today!
OnePunchMonk101010
/
kora-gpt2-sst2-lora_compTrue_seed0
like
0
lora
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
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
.