mradermacher/MedGemma-4B-it-finetuned-GGUF

Same weights, converted (fewer layers) vs 2kfi/MedGemma-4B-it-finetuned. mradermacher/MedGemma-4B-it-finetuned-GGUF matches part of 2kfi/MedGemma-4B-it-finetuned (444 of its 883 tensors; the rest of 2kfi/MedGemma-4B-it-finetuned has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse