nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Attention 196/196, MLP 84/84, Norms 57/57, lm_head 1/1
9 derivatives checked
- bartowski/nvidia_Nemotron-Research-Reasoning-Qwen-1.5B-GGUF: Full fine-tune
- mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-i1-GGUF: Full fine-tune
- prithivMLmods/Research-Reasoning-Qwen-F32-GGUF: Full fine-tune
- DevQuasar/nvidia.Nemotron-Research-Reasoning-Qwen-1.5B-GGUF: Full fine-tune
- mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF: Full fine-tune
- ReallyFloppyPenguin/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF: Full fine-tune
- lmstudio-community/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF: Full fine-tune
- lucaswychan/Nemotron-Research-Reasoning-Qwen-1.5B-Reasoning-Embedding: Full fine-tune
- hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE: Full fine-tune
2 other repos hold byte-for-byte identical weight files.