LLM Reference

Llama 3.1 Nemotron 70B Reward

About

NVIDIA reward model based on Llama 3.1 70B, used for RLHF and preference ranking.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
NVIDIA NIMServerless

Rankings

Specifications

FamilyNvidia
Released2024-10-01
Parameters70B
Context4K
ArchitectureDecoder Only
Specializationreward_model
Trainingpretraining

Providers(1)