AceReason - a nvidia Collection

nvidia 's Collections

Describe Anything

OpenMathReasoning

OpenCodeReasoning

OpenCodeReasoning-II

Llama Nemotron Feedback-Edit Inference-Time Scaling

Scoring Verifiers

Nemotron-UltraLong

Cosmos Transfer1

Cosmos Tokenize1

Cosmos Predict1

Llama-3.1-Nemotron-70B

NVILA-Speech-Audio-Setups

QLIP

Cosmos

DMC

AceMath

Cosmos Tokenizer

Eagle 2

NeMo Audio Codecs

Hymba

Optimized ONNX models for NVIDIA RTX GPUs

Riva

Nemotron 4 340B

SteerLM

Canary

RLHF

Llama3-ChatQA-1.5

SSMs

BigVGAN

RADIO

Model Optimizer

Llama3-ChatQA-2

NeMo Curator - Classifier Models

AceReason

updated about 20 hours ago

Math and Code reasoning model trained through reinforcement learning (RL)