NousResearch Hermes 3 Llama 3.1 70B - Multi GPU

The NousResearch/Hermes-3-Llama-3.1-70B model is a 70 billion parameter generalist language model that offers advanced capabilities such as agentic abilities, roleplaying, reasoning, and multi-turn conversation, with improved steering and control given to the end user via its ChatML prompt format.

Model ID: NousResearch/Hermes-3-Llama-3.1-70B

Supported Language(s): en

License: Llama3

Modality: text

Hardware Support

Software Included

Creating an App using the Control Panel

Click the Deploy to DigitalOcean button to create a Droplet based on this 1-Click App. If you aren’t logged in, this link will prompt you to log in with your DigitalOcean account.

Creating an App using the API

In addition to creating a Droplet from the NousResearch Hermes 3 Llama 3.1 70B - Multi GPU 1-Click App using the control panel, you can also use the DigitalOcean API. As an example, to create a 4GB NousResearch Hermes 3 Llama 3.1 70B - Multi GPU Droplet in the SFO2 region, you can use the following curl command. You need to either save your API access token) to an environment variable or substitute it in the command below.

curl -X POST -H 'Content-Type: application/json' \
         -H 'Authorization: Bearer '$TOKEN'' -d \
        '{"name":"choose_a_name","region":"sfo2","size":"s-2vcpu-4gb","image": "digitaloceanai-nresearchhermes3"}' \
        "https://api.digitalocean.com/v2/droplets"

Getting Started After Deploying NousResearch Hermes 3 Llama 3.1 70B - Multi GPU

Quickly Get Started With Your 1-Click Models

1. Access the Droplet Console:

   • Navigate to the GPU Droplets page.
   • Locate your newly created 1-Click Model Droplet and click on its name.
   • At the top of your screen select and launch the Web Console. It will open in a new window.

2. Login via SSH:

• If you selected an SSH key during droplet creation, follow these steps:- Open your preferred SSH client (e.g., PuTTY, Terminal).

• Use the droplet’s public IP address to log in as root:

ssh root@your_droplet_public_IP

+ Ensure your SSH key is added to the SSH agent, or specify the key file directly:

ssh -i /path/to/your/private_key root@your_droplet_public_IP

+ Once connected, you will be logged in as the root user without needing a password.

3. Check the Message of the Day (MOTD) for Access Token:

   • Upon successful login via console or SSH, the Message of the Day (MOTD) will be displayed.
   • This message includes important information such as the bearer token. Take note of this token as you’ll need it to use the inference API for your model.

Troubleshooting

1. Please note that the models require a couple of minutes to load, as the docker containers is started for the respective model. During this process any API calls to the model will timeout.
2. To ensure that Caddy is working, run:

sudo systemctl status caddy

Usage Examples

Using cURL

You can make a local API call using this cURL command:

curl -X 'POST' \
  'http://<your_droplet_ip>/v1/chat/completions' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer '<your_token_here>'' \
  -d '{
    "model": "<model_name>",
    "messages": [{"role":"user", "content":"What is Deep Learning?"}],
    "max_tokens": 64,
    "stream": false
}'

Using Python with huggingface_hub

from huggingface_hub import InferenceClient

client = InferenceClient(
    base_url="http://0.0.0.0:8080/v1",
    api_key="-",
)

output = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {"role": "user", "content": "Count to 10"},
    ],
    stream=True,
    max_tokens=1024,
)

for chunk in output:
    print(chunk.choices[0].delta.content, end="")

Using Python with OpenAI library

from openai import OpenAI

client = OpenAI(
    api_key="-",
    base_url="http://0.0.0.0:8080/v1"
)
response = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {"role": "user", "content": "What is deep learning?"},
    ],
    stream=True,
    max_tokens=64,
)

# Iterate and print stream
for message in response:
    print(message.choices[0].delta.content, end="")

This works with every OpenAI client including JavaScript.