rikunarita/Qwen3.5-2B-Claude-Opus-4.6-high-resoning-Base
LoRA-style vs Qwen/Qwen3.5-2B-Base. 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 23 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 24/268, Norms 0/183, Embeddings 0/5, MLP 72/175, other 0/1
2 derivatives checked
- mradermacher/Qwen3.5-2B-Claude-Opus-4.6-high-resoning-Base-i1-GGUF: Quantization
- mradermacher/Qwen3.5-2B-Claude-Opus-4.6-high-resoning-Base-GGUF: Same weights, converted