Artificial intelligence startups Lambda Inc. and Nous Research today announced the launch of a new large language model called Hermes 3, which it says is a “personalized, unrestricted” version of Meta Platforms Inc.’s open-source Llama 3.1 model.

The largest 405 billion parameter version of the Hermes 3 model is unusual in that it displays evidence of having an “existential crisis” when given a blank prompt followed by the question “Who are you?”.

In a blog post, Lambda’s researchers say this “feature,” for want of a better word, was totally unexpected and indicative of “anomalous behavior” that occurs when scaling AI models beyond a certain threshold. To understand what’s going on, the creators of Hermes 3 are inviting users to interact with the model via a Discord server and “uncover the labyrinth lurking within the weights.”

Lambda  is an AI infrastructure company that was born out of the ashes of a third-party Google Glass facial recognition app, while Nous Research is an AI research startup that’s focused on creating “potent open-source code and efficient large language models.” The two companies previously worked together on Hermes 3’s predecessors, including the original Hermes, Hermes 2 and Open Hermes 2.5, which have collectively been downloaded more than 33 million times in total.

What’s different about Hermes 3, besides being more advanced, is that it comes with unlocked and uncensored open weights. This means it’s more steerable, allowing users to adapt its responses to suit their specific needs. That’s in contrast to many of the other leading LLMs around today, which are often much more rigid and difficult to customize.

The model is available in three parameter sizes, 8 billion, 70 billion and 405 billion, and was trained on a diverse dataset in a process designed to improve its creativity, reasoning and adherence to user’s instructions. It boasts strong capabilities in terms of its long-term context retention, making it capable of more humanlike conversations where it can remember the specific context, as well as multiturn conversation management. It also excels at complex role-playing, which is something that often leaves proprietary LLMs flummoxed.

Another area of progress is Hermes 3’s agentic powers. AI models with agentic capabilities are those that can perform a series of tasks on the behalf of users, and it’s a big area of buzz in AI development lately. Hermes 3 is able to use XML tags for structured outputs, generate internal monologues for transparent decision-making, and partake in visual communications using Mermaid diagrams, the creators said. It also employs step-labeled reasoning and planning to enhance its transparency.

One of its most impressive agentic capabilities is its ability to generate code with high proficiency, as well as detailed explanations of that code and the corresponding documentation to go with it. So it has big potential in the area of software development and bug detection.

According to Nous Research, the Hermes 3 model was trained using Lambda’s 1-Click Cluster infrastructure and was optimized for efficiency using techniques such as Neural Magic Inc.’s FP8 quantization, reducing its virtual RAM and disk requirements by about 50%. It still doesn’t match the performance of proprietary LLMs such as OpenAI’s most advanced model, GPT-4o or Anthropic’s Claude 3.5 Sonnet, but it demonstrated superior performance versus all open-source LLMs in a varied set of benchmark tests.

The creators say the most appealing aspect of Hermes 3 is its sheer versatility. The model is said to excel in applications that require decision-making, advanced reasoning, strategic planning and creativeness.

“Since the start of my journey in AI, I wanted to bring about the realization of an open-source frontier-level model that aligns with you, the user — not some corporation or higher authority before the user. Today, with Hermes 3 405B, we’ve achieved that goal,” wrote Nous Research co-founder Teknium.

Holger Mueller of Constellation Research Inc. said Hermes 3 is a great example of perhaps the most beautiful thing about open-source software, which is the ability to take something that exists and make it even better.

“By taking Llama 3.1 and training it further and letting users decide on the weights to be applied to responses, that is exactly what Lambda and Nous Research have done,” the analyst said. “If it leads to better results it will be a blessing for users, but it could also cause problems if it leads to more experimentation and time lost. Hermes 3 will have to show it can make a difference in enterprise AI applications.”

Both Lambda and Nous Research said they’re eager for people to engage with Hermes 3 and share their experiences. For casual users, Hermes 3 is available through the Lambda Chat interface. It can also  be accessed via Lambda’s Chat Completions application programming interface. To do so, they can generate a Cloud API key through Lambda’s dashboard and set about testing the model’s capabilities without any complex setup required.

For dedicated access, users can deploy Hermes 3 on a single Lambda node, or a more advanced multinode configuration if they desire to fine-tune it further.

Images: Nous Research & Lambda Labs