ermiaazarkhalili/Granite-4.1-3B-SFT-Claude-Opus-Reasoning-Unsloth
LoRA-style vs ibm-granite/granite-4.1-3b. 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 0/81, MLP 120/120, Attention 160/160
4 derivatives checked
- mradermacher/Granite-4.1-3B-SFT-Claude-Opus-Reasoning-Unsloth-i1-GGUF: Quantization
- Orionchik/Granite-4.1-3B-SFT-Claude-Opus-Reasoning-Unsloth-i1-GGUF: Quantization
- mradermacher/Granite-4.1-3B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF: Same weights, converted
- nightmedia/granite-4.1-3B-Agent3-q8-hi-mlx: Quantization