Chat Mixture of Agents
A Mixture-of-Agents (MoA) synthesis mix optimized for fast and balanced chat use cases. This mix leverages multiple 'proposer' models, including Llama 3.1 70B on Groq and DeepSeek v2.5, with an 'aggregation' model that synthesizes their outputs.
API
Example
Models
This mix uses the models below:
claude-3-5-sonnet-20241022
Provided by anthropic
gpt-4-turbo-2024-04-09
Provided by openai
gpt-4o-2024-08-06
Provided by openai
Readme
Chat Mixture of Agents
This is a Mixture-of-Agents (MoA) synthesis mix optimized for chat. This mix leverages two 'proposer' models (Llama 3.1 70B on Groq and DeepSeek v2.5) with an 'aggregation' model (Llama 3.1 70B) that synthesizes their outputs. The goal is to produce fast and balanced responses by sourcing responses from multiple models.
This model is available on Decent, an open-source chat client on Android and iOS.
To learn more about mixture of agents, check out our Github repo here.
Categories
- 🦾 Mixture of Agents
- 💬 General
- 🌐 Open-Source
Composition
This mix produces responses from the following models:
| Model Name | Type |
|---|---|
| Meta-Llama-3.1-70B-Instruct | Proposer |
| DeepSeek-Chat | Proposer |
| Meta-Llama-3.1-70B-Instruct | Aggregator |