pfnet/Preferred-MedLLM-Qwen-72B
LoRA-style vs Qwen/Qwen2.5-72B. 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 80 of 80 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, MLP 240/240, Attention 320/560, Norms 0/161, lm_head 0/1
3 derivatives checked
- mmnga/Preferred-MedLLM-Qwen-72B-gguf: Quantization
- mradermacher/Preferred-MedLLM-Qwen-72B-i1-GGUF: Quantization
- mradermacher/Preferred-MedLLM-Qwen-72B-GGUF: Quantization