OpenPipe/Deductive-Reasoning-Qwen-32B
Full fine-tune vs Qwen/Qwen2.5-32B-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 122/129, MLP 192/192, Attention 447/448, lm_head 1/1
7 derivatives checked
- bartowski/OpenPipe_Deductive-Reasoning-Qwen-32B-GGUF: Same weights, converted
- MaziyarPanahi/Deductive-Reasoning-Qwen-32B-GGUF: Quantization
- featherless-ai-quants/OpenPipe-Deductive-Reasoning-Qwen-32B-GGUF: Quantization
- DevQuasar-10/OpenPipe.Deductive-Reasoning-Qwen-32B-GGUF: Quantization
- YOYO-AI/Qwen2.5-32B-YOYO-reasoning-v2: Full fine-tune
- maldv/QReasoner2.5-32B-Instruct: Full fine-tune
- YOYO-AI/Qwen2.5-32B-YOYO-reasoning: Full fine-tune