Taimwe/securecoder-30b-pro-v3-merged
LoRA-style vs unsloth/Qwen3-Coder-30B-A3B-Instruct. 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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/193, MLP 0/2613, Attention 192/192, lm_head 0/1
2 derivatives checked
- mradermacher/securecoder-30b-pro-v3-merged-i1-GGUF: Quantization
- mradermacher/securecoder-30b-pro-v3-merged-GGUF: Quantization