OpenBuddy/OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT
Full fine-tune vs Qwen/Qwen3-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 161/257, MLP 192/192, Attention 256/256
3 derivatives checked
- bartowski/OpenBuddy_OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT-GGUF: Same weights, converted
- mradermacher/DeepSeek-R1-0528-Distill-Qwen3-32B-Preview0-QAT-GGUF: Quantization
- DevQuasar/OpenBuddy.OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT-GGUF: Same weights, converted