Jackrong/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled
LoRA-style vs Qwen/Qwen3.5-0.8B. 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, out_proj, q_proj, up_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 42/220, Norms 0/135, Embeddings 0/5, MLP 72/127, other 0/1
5 derivatives checked
- mradermacher/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-i1-GGUF: Quantization
- mradermacher/Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-GGUF: Same weights, converted
- Jackrong/MLX-Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distilled-6bit: Quantization
- larped/Jackrong-Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distiled-OBLITERATED: Partial fine-tune (fewer layers)
- larped/Jackrong-Qwen3.5-0.8B-Claude-4.6-Opus-Reasoning-Distiled-heretic: Partial fine-tune (fewer layers)