Text Generation
Transformers
Safetensors
PyTorch
nvidia
conversational

NVIDIA-Nemotron-Nano-9B-v2 with Docker

#27
by MOHASOFT - opened

This is a simple repository to launch the nvidia/NVIDIA-Nemotron-Nano-9B-v2 model using vLLM and Docker. A GPU with VRAM greater than 24GB (e.g., NVIDIA RTX 3090) is recommended.

This repository provides a nemo.sh script to launch a vLLM OpenAI-compatible server for the nvidia/NVIDIA-Nemotron-Nano-9B-v2 model:

https://github.com/comewelcome/nemotron

Sign up or log in to comment