mergekit-community/QwQ-openhands-Code-32B
Full fine-tune vs OpenHands/openhands-lm-32b-v0.1. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 129/129, MLP 192/192, Attention 448/448
2 derivatives checked
- mradermacher/QwQ-openhands-Code-32B-i1-GGUF: Quantization
- mradermacher/QwQ-openhands-Code-32B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.