The nvidia/llama-nv-embed-reasoning-3b galaxy
6 models are built on nvidia/llama-nv-embed-reasoning-3b: 3 quantized, 2 fine-tuned, 1 adapters and 0 merges. Together they were downloaded 2,158 times in the last 30 days.
Most downloaded direct derivatives
- mradermacher/llama-nv-embed-reasoning-3b-GGUF (quantized), 260 downloads in 30 days
- DataScience-UIBK/OBLIQ-IR-3B (finetune), 34 downloads in 30 days
- DataScience-UIBK/OBLIQ-IR-3B-no-distill (finetune), 18 downloads in 30 days
- DataScience-UIBK/OBLIQ-IR-3B-LoRA (adapter), 15 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.