OpenHands/openhands-lm-7b-v0.1
Full fine-tune vs Qwen/Qwen2.5-Coder-7B-Instruct. Fine-tune: 93% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1
5 derivatives checked
- bartowski/all-hands_openhands-lm-7b-v0.1-GGUF: Same weights, converted
- mradermacher/openhands-lm-7b-v0.1-i1-GGUF: Quantization
- mradermacher/openhands-lm-7b-v0.1-GGUF: Same weights, converted
- DevQuasar-6/all-hands.openhands-lm-7b-v0.1-GGUF: Same weights, converted
- lmstudio-community/openhands-lm-7b-v0.1-GGUF: Quantization