Hugging Face's logo

AISE-TUDelft
/
Custom-Activations-GPT-Adaptive-GELU

Text Generation
Transformers
PyTorch
activations_gpt_neo
Inference Endpoints
Model card Files Community
Edit model card

Basemodel: GPT-Neo

Configs: Vocab size: 10,000 Hidden size: 512 Max position embeddings: 512 Number of layers: 2 Number of heads: 4 Window size: 256 Intermediate-size: 1024

Results:

  • Task: glue Score: 59.30 Confidence Interval: [58.92, 59.73]
  • Task: blimp Score: 57.24 Confidence Interval: [56.47, 58.03]
Downloads last month
1

Dataset used to train AISE-TUDelft/Custom-Activations-GPT-Adaptive-GELU

Collection including AISE-TUDelft/Custom-Activations-GPT-Adaptive-GELU