mhdang/gelatwo-common-gen-gpt2-large
Full fine-tune vs openai-community/gpt2-large. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Attention 144/144, Norms 146/146, MLP 144/144, Embeddings 1/2
Full fine-tune vs openai-community/gpt2-large. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Attention 144/144, Norms 146/146, MLP 144/144, Embeddings 1/2