MaziyarPanahi/falcon3-7b-reasoning-v0.1
LoRA-style vs tiiuae/Falcon3-7B-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 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 84/84, Attention 112/112, lm_head 0/1
1 derivatives checked
- mradermacher/falcon3-7b-reasoning-v0.1-i1-GGUF: Quantization