LLM Reference

Nous Hermes 13B

About

The Nous Hermes 13B is a cutting-edge large language model fine-tuned on over 300,000 instructions and built upon the Llama 13B architecture. Developed by Nous Research, with significant contributions from Teknium, Karan4D, and Redmond AI, the model excels in generating coherent long-form responses and performs comparably to GPT-3.5-turbo. It avoids OpenAI's content censorship, offering more open dialogues. Additionally, Nous Hermes 13B achieves top rankings in various benchmark tests and is available for download on Hugging Face, with future plans for model quantization and further benchmarking 123.

Capabilities

MultimodalFunction CallingTool UseJSON Mode

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
Lepton AI API
Serverless

Specifications

FamilyHermes
Parameters13B
ArchitectureDecoder Only
Specializationgeneral