rohanprichard/Llama-3.1-SuperNova-Lite-q3f16-MLC

Llama-3.2-1B-Instruct-MLC

This is the Llama-3.1-SuperNova-Lite model in MLC format q3f16_1. The model can be used for projects MLC-LLM and WebLLM.

Example Usage

Here are some examples of using this model in MLC LLM. Before running the examples, please install MLC LLM by following the installation documentation.

Chat

In command line, run

mlc_llm chat HF://rohanprichard/Llama-3.1-SuperNova-Lite

REST Server

In command line, run

mlc_llm serve HF://rohanprichard/Llama-3.1-SuperNova-Lite

Python API

from mlc_llm import MLCEngine

# Create engine
model = "HF://rohanprichard/Llama-3.1-SuperNova-Lite"
engine = MLCEngine(model)

# Run chat completion in OpenAI API.
for response in engine.chat.completions.create(
    messages = [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "How many r's are in the word strawberry?"
                },
            ],
        },
    ],
    model=model,
    stream=True,
):
    for choice in response.choices:
        print(choice.delta.content, end="", flush=True)
print("\n")

engine.terminate()

Documentation

For more information on MLC LLM project, please visit the documentation and GitHub repo. Model card based on the template from the MLC team.