bunnycore/QwQen-3B-LCoT-R1
LoRA-style vs bunnycore/QwQen-3B-LCoT. 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 0/73, MLP 108/108, Attention 144/252
2 derivatives checked
- mradermacher/QwQen-3B-LCoT-R1-i1-GGUF: Quantization
- mradermacher/QwQen-3B-LCoT-R1-GGUF: Same weights, converted