microsoft/MediPhi-Clinical

Full fine-tune vs microsoft/Phi-3.5-mini-instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 39/65, MLP 64/64, Attention 64/64, lm_head 1/1

3 derivatives checked

• mradermacher/MediPhi-Clinical-GGUF: Same weights, converted
• mradermacher/MediPhi-Clinical-i1-GGUF: Quantization
• DevQuasar/microsoft.MediPhi-Clinical-GGUF: Quantization

On the Hub · Downloads on Model Pulse