LLM ReferenceLLM Reference

Nous Hermes Llama 2 70B

About

70B Hermes built on Llama 2 trained on 300K+ instructions with extended response generation and low hallucination rates.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
Fireworks AI$0.90$0.90Provisioned

Rankings

Specifications

FamilyHermes
Released2023-12-15
Parameters70B
ArchitectureDecoder Only
Specializationgeneral
Trainingfinetuning

Created by

Human-centric AI model innovation

New York, New York, United States
Founded 2023
Website

Providers(1)