Compumacy/Psych_medgemma
LoRA-style vs unsloth/medgemma-27b-text-it. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 62 of 62 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/373, MLP 186/186, Attention 248/248
4 derivatives checked
- mradermacher/Compumacy-Experimental-MG-i1-GGUF: Quantization
- mradermacher/Compumacy-Experimental-MG-GGUF: Quantization
- andosen/Psych_medgemma-mlx-6Bit: Quantization
- andosen/Psych_medgemma-mlx-5Bit: Quantization