Prithwiraj731/Granite-3.1-2b-TwoWheeler
LoRA-style vs ibm-granite/granite-3.1-2b-instruct. 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
1 derivatives checked
- mradermacher/Granite-3.1-2b-TwoWheeler-GGUF: Same weights, converted