elvee/
hermes-2-pro-llama-3:8b-Q5_K_M

833 1 year ago

This is the llama.cpp GGUF Quantised version of Hermes 2 Pro Llama-3 8B from Nous Research with function calling capabilities.

1 year ago

1451afe6947f · 5.7GB ·

model
llama
·
8.03B
·
Q5_K_M
template
<|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assi
system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man
params
{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

Readme

Hermes 2 Pro - Llama-3 8B - GGUF

Image of the Hermes 2 Pro logo

Description

Hermes 2 Pro is a state-of-the-art LLM developed by Nous Research. It’s based on the Llama 3 architecture with 8 billion parameters. It offers advanced capabilities in natural language processing, creative writing, coding assistance, and more.

Prompt Format

Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue. It uses a system prompt to establish rules and roles, and steer the interaction between the user and the model.

Function Calling

The Hermes-Function-Calling repository contains code for the model to perform function calling based on the provided schema. It allows users to query the model and retrieve information related to stock prices, company fundamentals, financial statements, and more.

Resources