Nous Hermes

MonadGPT is a finetune of Mistral-Hermes on 11,000 early modern texts in English, French and Latin (17th century)

Pclanglais/MonadGPT · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

https://huggingface.co/Pclanglais/MonadGPT

teknium/OpenHermes-2-Mistral-7B · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

https://huggingface.co/teknium/OpenHermes-2-Mistral-7B

TheBloke/Nous-Hermes-Llama-2-7B-GGML · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

https://huggingface.co/TheBloke/Nous-Hermes-Llama-2-7B-GGML

NousResearch/Nous-Hermes-Llama2-13b · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b

• First production model fully post-trained on the Psyche distributed learning network

• Achieves equivalent throughput to centralized training while hiding communication costs between internet-distributed nodes using the DisTrO optimizer

Introducing Hermes 4.3: Local Intelligence Globally Trained - NOUS RESEARCH

Today we’re releasing Hermes 4.3 (🤗 Hugging Face), an update to our flagship Hermes series of models. Hermes 4.3 was trained with an extended context length (up to 512K) and nearly matches (and in some cases exceeds) the performance of Hermes 4 70B at half the parameter cost. Based on Seed-OSS-36B-Base, Hermes 4.3 […]

https://nousresearch.com/introducing-hermes-4-3/