nvidia/Riva-Translate-4B-Instruct download history
nvidia/Riva-Translate-4B-Instruct is a 4.2B-parameter text generation model by nvidia. In the last 30 days it was downloaded 1,745 times (643 in the last 7 days), and 7,051 times in total.
It ranks #23,855 on the Hub by monthly downloads and #6,372 among text generation models.
It has 23 likes, 1 of them in the last week.
It is a fine-tune of nvidia/Mistral-NeMo-12B-Base.
8 models build on Riva-Translate-4B-Instruct: 8 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 2,491 times in the last 30 days. See the Riva-Translate-4B-Instruct galaxy.
Most downloaded derivatives
- mradermacher/Riva-Translate-4B-Instruct-i1-GGUF (quantized), 373 downloads in 30 days
- mradermacher/Riva-Translate-4B-Instruct-GGUF (quantized), 204 downloads in 30 days
- tensorblock/nvidia_Riva-Translate-4B-Instruct-GGUF (quantized), 81 downloads in 30 days
- cyberunit/Riva-Translate-4B-Instruct-Q4_K_M-GGUF (quantized), 30 downloads in 30 days
- asdgad/Riva-Translate-4B-Instruct-Q8_0-GGUF (quantized), 28 downloads in 30 days
- neody/riva-translate-4b-instruct-gptq-int8 (quantized), 16 downloads in 30 days
- neody/riva-translate-4b-instruct-gptq-int8-w64 (quantized), 10 downloads in 30 days
- TrentB/Riva-Translate-4B-Instruct-ONNX (quantized), 4 downloads in 30 days
Open nvidia/Riva-Translate-4B-Instruct on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.