yasserrmd/SinaReason-Magistral-2509
LoRA-style vs mistralai/Magistral-Small-2509. 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 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/131, MLP 120/192, Attention 160/256, other 0/4, lm_head 0/1
2 derivatives checked
- mradermacher/SinaReason-Magistral-2509-i1-GGUF: Full fine-tune (fewer layers)
- mradermacher/SinaReason-Magistral-2509-GGUF: Full fine-tune (fewer layers)