Atomic-Ai/GPT-Chat-German-Nano
Full fine-tune vs dbmdz/german-gpt2. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Attention 48/48, Norms 50/50, MLP 48/48, Embeddings 1/1
Full fine-tune vs dbmdz/german-gpt2. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Attention 48/48, Norms 50/50, MLP 48/48, Embeddings 1/1