AethronPhantom/Nexa_Sci_distilled_Falcon-10B
LoRA-style vs tiiuae/Falcon3-10B-Base. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 80/160, lm_head 0/1
2 derivatives checked
- mradermacher/Nexa_Sci_distilled_Falcon-10B-i1-GGUF: Quantization
- mradermacher/Nexa_Sci_distilled_Falcon-10B-GGUF: Same weights, converted