lukasstraub2/gpt2-aidungeon2

Full fine-tune vs openai-community/gpt2-xl. Fine-tune: 95% of the weights changed, across 48 of 48 layers.

Tensors changed: Attention 192/192, Norms 192/194, MLP 192/192, Embeddings 0/2

1 derivatives checked

• lukasstraub2/gpt2-aidungeon2-gguf: Same weights, converted

On the Hub · Downloads on Model Pulse