Riva-Translate-4B-Instruct-v2
nvidia/Riva-Translate-4B-Instruct-v2
- kind
- original
- quant
- bf16 (16-bit)
- family
- misc
- modality
- text-generation
- root model
- nvidia/Mistral-NeMo-12B-Base
- provider
- nvidia
- license
- —
- language
- —
- context
- 8k
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 180
- likes
- 4
- created
- —
- last modified
- 2026-07-27T17:59:38+00:00 (2026)
- huggingface
- https://huggingface.co/nvidia/Riva-Translate-4B-Instruct-v2
- tags
- transformerssafetensorsmistraltext-generationconversationalbase_model:nvidia/Mistral-NeMo-12B-Basebase_model:finetune:nvidia/Mistral-NeMo-12B-Basetext-generation-inferenceendpoints_compatibleregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.