OpenHands/openhands-lm-32b-v0.1
Full fine-tune vs Qwen/Qwen2.5-Coder-32B-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 127/129, MLP 192/192, Attention 448/448, lm_head 1/1
9 derivatives checked
- bartowski/all-hands_openhands-lm-32b-v0.1-GGUF: Same weights, converted
- mradermacher/openhands-lm-32b-v0.1-i1-GGUF: Quantization
- DevQuasar-12/all-hands.openhands-lm-32b-v0.1-GGUF: Same weights, converted
- mradermacher/openhands-lm-32b-v0.1-GGUF: Quantization
- lmstudio-community/openhands-lm-32b-v0.1-GGUF: Quantization
- mergekit-community/QwQ-openhands-Code-32B: Full fine-tune
- marcuscedricridia/Springer1.2-32B-Code: Full fine-tune
- mergekit-community/openhands-Nemotron-32B-karcher: Full fine-tune
- YOYO-AI/QwQ-openhands-coder-32B: Full fine-tune