open-r1/OlympicCoder-32B
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 129/129, MLP 192/192, Attention 448/448, lm_head 1/1
4 derivatives checked
- bartowski/open-r1_OlympicCoder-32B-GGUF: Full fine-tune
- DevQuasar-10/open-r1.OlympicCoder-32B-GGUF: Same weights, converted
- mradermacher/OlympicCoder-32B-GGUF: Full fine-tune
- lmstudio-community/OlympicCoder-32B-GGUF: Full fine-tune