moonlight-labs/moonlight-qwen3-4b-v7
LoRA-style vs Qwen/Qwen3-4B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 72/144
2 derivatives checked
- mradermacher/moonlight-qwen3-4b-v7-i1-GGUF: Quantization
- mradermacher/moonlight-qwen3-4b-v7-GGUF: Same weights, converted