sequelbox/Qwen3-4B-Thinking-2507-DAG-Reasoning
LoRA-style vs Qwen/Qwen3-4B-Thinking-2507. 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 0/145, MLP 0/108, Attention 144/144
3 derivatives checked
- mradermacher/Qwen3-4B-Thinking-2507-DAG-Reasoning-i1-GGUF: Quantization
- mradermacher/Qwen3-4B-Thinking-2507-DAG-Reasoning-GGUF: Same weights, converted
- prithivMLmods/Qwen3-4B-Thinking-2507-DAG-GGUF: Partial fine-tune