RamzyBakir/Secure-SmolLM3-3B
LoRA-style vs HuggingFaceTB/SmolLM3-3B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 144/144
2 derivatives checked
- mradermacher/CySent-SmolLM3-3B-i1-GGUF: Quantization
- mradermacher/CySent-SmolLM3-3B-GGUF: Same weights, converted