Model reference · open weights
Hermes-3-Llama-3.1 is an open-weight language model from NousResearch, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Hermes 3 - Llama-3.1 8B Model Description Hermes 3 is the latest version of our flagship Hermes series of LLMs by Nous Research. For more details on new capabilities, training results, and more, see the Hermes 3 Technical Report. Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board. The ethos of the Hermes series of models is focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user. The Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills. Benchmarks Hermes 3 is competitive, if not superior, to Llama-3.1 Instruct models at general capabilities, with varying strengths and weaknesses attributable between the two. Full benchmark comparisons below: Prompt Format Hermes 3 uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue. System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model. This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns. This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI. Prompt with system instruction (Use whatever system prompt you like, this is just an example!): This prompt is available as a chat template, which means you can format messages using the tokenizer.applychattemplate() method: When tokenizing messages for generation, set addgenerationprompt=True when calling applychattemplate(). This will append <|imstart|assistant\n to your prompt, to ensure that the model continues with an assistant response. To utilize the prompt format without a system prompt, simply leave the lin
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | NousResearch |
|---|---|
| Type | Language models |
| Parameters (lead) | 8.0B |
| Context | 128k tokens |
| Variants | 2 |
| Runs with | transformers |
| Based on | meta-llama/Meta-Llama-3.1-8B |
| Released | 2024-07-28 |
| Popularity | 413k downloads / month |
| Likes | 492 |
| Licence | Open, with conditions |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Using it via the API
Once AxForge deploys hermes-3-llama-3-1 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (hermes-3-llama-3-1 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"hermes-3-llama-3-1","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under llama3, which carries conditions (e.g. attribution or an acceptable-use clause). Worth a read before production use — we can walk you through it. Read the licence ↗