ZeroXClem/Qwen3-4B-NexusPrime
LoRA-style vs prithivMLmods/Bootes-Qwen3_Coder-Reasoning. 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: Norms 0/145, MLP 108/108, Attention 144/144
1 derivatives checked
- mradermacher/Qwen3-4B-NexusPrime-GGUF: Same weights, converted