nvidia/OpenReasoning-Nemotron-7B
Full fine-tune vs Qwen/Qwen2.5-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1
7 derivatives checked
- bartowski/nvidia_OpenReasoning-Nemotron-7B-GGUF: Same weights, converted
- gabriellarson/OpenReasoning-Nemotron-7B-GGUF: Same weights, converted
- mradermacher/OpenReasoning-Nemotron-7B-GGUF: Same weights, converted
- lmstudio-community/OpenReasoning-Nemotron-7B-GGUF: Quantization
- tensorblock/nvidia_OpenReasoning-Nemotron-7B-GGUF: Quantization
- DevQuasar/nvidia.OpenReasoning-Nemotron-7B-GGUF: Same weights, converted
- Bifrost-AI/Mirage-OpenReasoning-Nemotron-7B: Full fine-tune