nvidia/OpenCodeReasoning-Nemotron-14B
Full fine-tune vs Qwen/Qwen2.5-14B-Instruct. Fine-tune: 95% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 97/97, MLP 144/144, Attention 336/336, lm_head 1/1
6 derivatives checked
- bartowski/nvidia_OpenCodeReasoning-Nemotron-14B-GGUF: Same weights, converted
- mradermacher/OpenCodeReasoning-Nemotron-14B-i1-GGUF: Quantization
- lmstudio-community/OpenCodeReasoning-Nemotron-14B-GGUF: Quantization
- mradermacher/OpenCodeReasoning-Nemotron-14B-GGUF: Quantization
- DevQuasar/nvidia.OpenCodeReasoning-Nemotron-14B-GGUF: Same weights, converted
- ReallyFloppyPenguin/OpenCodeReasoning-Nemotron-14B-GGUF: Same weights, converted