InstructRetro - a nvidia Collection

nvidia 's Collections

Hymba

Optimized ONNX models for NVIDIA RTX GPUs

Cosmos Tokenizer

Llama-3.1-Nemotron-70B

Nemotron 4 340B

SteerLM

Canary

RLHF

Llama3-ChatQA-1.5

SSMs

BigVGAN

RADIO

NIM Serverless Inference API

Model Optimizer

Llama3-ChatQA-2

NeMo Curator - Classifier Models

InstructRetro

updated Oct 1

InstructRetro is an autoregressive decoder-only language model (LM) with retrieval-augmented pretraining and instruction tuning.