Mistral AI and NVIDIA unveiled Mistral NeMo 12B, a brand-new, cutting-edge language model
Mistral NeMo utilises NVIDIA's optimised hardware and software ecosystem with Mistral AI to excel in many applications
Mistral AI, said, “NVIDIA is fortunate to collaborate with the NVIDIA team, leveraging their top-tier hardware and software
The NVIDIA AI Enterprise model had unsurpassed accuracy, flexibility, efficiency, enterprise-grade support, and security
Mistral NeMo, a 12-billion-parameter Apache 2.0 model, encourages innovation and supports the AI community
Mistral NeMo, an NVIDIA NIM inference microservice, optimises inference performance with TensorRT-LLM engines
Mistral NeMo NIM performs well on a single NVIDIA L40S, GeForce RTX 4090, or RTX 4500 GPU and security and privacy
NVIDIA engineers and Mistral AI have improved Mistral NeMo's training and inference
The model was trained using Megatron-LM, a component of NVIDIA NeMo, using 3,072 H100 80GB Tensor Core GPUs on DGX Cloud, which has NVIDIA AI architecture