webAI-Official/TwIL-LM3
LoRA-style vs HuggingFaceTB/SmolLM3-3B. 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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 108/108, Attention 144/144
2 derivatives checked
- usermma/TwIL-LM3-mlx-8Bit: Quantization
- NANI-Nithin/TwIL-LM3-GGUF: Same weights, converted