ertghiu256/ministral-3-3b-glm-distillation
LoRA-style vs mistralai/Ministral-3-3B-Reasoning-2512. 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 26 of 26 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/103, MLP 78/150, Attention 104/200, other 0/4
1 derivatives checked
- ertghiu256/ministral-3-3b-glm-distillation-gguf: Same weights, converted (fewer layers)