alibidaran/medical_transcription_generator
Full fine-tune vs openai-community/gpt2. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: Norms 50/50, Attention 60/60, MLP 48/48, Embeddings 1/2
2 derivatives checked
- mradermacher/medical_transcription_generator-i1-GGUF: Quantization
- mradermacher/medical_transcription_generator-GGUF: Same weights, converted