Nous-Hermes-2-Mixtral-8x-DPO

About

What Nous-Hermes-2-Mixtral-8x-DPO is

Nous Hermes 2 - Mixtral 8x7B - DPO Model description Nous Hermes 2 Mixtral 8x7B DPO is the new flagship Nous Research model trained over the Mixtral 8x7B MoE LLM. The model was trained on over 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape, achieving state of the art performance on a variety of tasks. This is the SFT + DPO version of Mixtral Hermes 2, we have also released an SFT only version, for people to find which works best for them, which can be found here: https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT We are grateful to Together.ai for sponsoring our compute during the many experiments both training Mixtral and working on DPO! Table of Contents 1. Example Outputs 2. Benchmark Results - GPT4All - AGIEval - BigBench - Comparison to Mixtral-Instruct 3. Prompt Format 4. Inference Example Code 5. Quantized Models Example Outputs Writing Code for Data Visualization Writing Cyberpunk Psychedelic Poems Performing Backtranslation to Create Prompts from Input Text Benchmark Results Nous-Hermes 2 on Mixtral 8x7B is a major improvement across the board on the benchmarks below compared to the base Mixtral model, and is the first model to beat the flagship Mixtral Finetune by MistralAI. GPT4All: Average: 75.70 AGIEval: Average: 46.05 BigBench: Average: 49.70 Benchmark Comparison Charts GPT4All AGI-Eval BigBench Reasoning Test Comparison to Mixtral Instruct: Our benchmarks show gains in many benchmarks against Mixtral Instruct v0.1, on average, beating the flagship Mixtral model. Prompt Format Nous Hermes 2 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

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

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

Call it like any OpenAI endpoint

Once AxForge deploys nous-hermes-2-mixtral-8x-dpo for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (nous-hermes-2-mixtral-8x-dpo 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":"nous-hermes-2-mixtral-8x-dpo","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More language models