Understanding the Llama-3.1-Nemotron-70b-instruct model

Model overviewLink to this anchor

Model namesLink to this anchor

meta/llama-3.1-nemotron-70b-instruct:fp8

Compatible InstancesLink to this anchor

Model introductionLink to this anchor

Introduced October 14, 2024, NVIDIA’s Nemotron 70B Instruct is a specialized version of the Llama 3.1 model designed to follow complex instructions. NVIDIA employed Reinforcement Learning from Human Feedback (RLHF) to fine-tune the model’s ability to generate relevant and informative responses.

Why is it useful?Link to this anchor

• As of October 2024, Llama 3.1 Nemotron 70B has achieved top rankings in multiple automatic alignment benchmarks. It boasts an overall score of 94.1 on RewardBench, with specific scores of 97.5 for chat performance and 98.1 in reasoning tasks.
• Just like with the original Llama 3.1, this model brings a context window up to 128K tokens and supports tool calling.
• With 70 billion parameters, this model is highly capable of generating sophisticated, human-like responses in a wide range of applications, from casual chatbots to complex technical systems.

How to use itLink to this anchor

Sending Managed Inference requestsLink to this anchor

To perform inference tasks with your Llama-3.1-Nemotron-70b-instruct deployed at Scaleway, use the following command:

curl -s \
-H "Authorization: Bearer <IAM API key>" \
-H "Content-Type: application/json" \
--request POST \
--url "https://<Deployment UUID>.ifr.fr-par.scaleway.com/v1/chat/completions" \
--data '{"model":"meta/llama-3.1-nemotron-70b-instruct:fp8", "messages":[{"role": "user","content": "There is a llama in my garden, what should I do?"}], "max_tokens": 500, "temperature": 0.7, "stream": false}'

Make sure to replace <IAM API key> and <Deployment UUID> with your actual IAM API key and the Deployment UUID you are targeting.

Receiving Inference responsesLink to this anchor

Upon sending the HTTP request to the public or private endpoints exposed by the server, you will receive inference responses from the managed Managed Inference server. Process the output data according to your application’s needs. The response will contain the output generated by the LLM model based on the input provided in the request.