Instructions to use nvidia/Llama-3.1-Minitron-4B-Width-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Llama-3.1-Minitron-4B-Width-Base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="nvidia/Llama-3.1-Minitron-4B-Width-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/Llama-3.1-Minitron-4B-Width-Base")
model = AutoModelForCausalLM.from_pretrained("nvidia/Llama-3.1-Minitron-4B-Width-Base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Llama-3.1-Minitron-4B-Width-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Llama-3.1-Minitron-4B-Width-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Llama-3.1-Minitron-4B-Width-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nvidia/Llama-3.1-Minitron-4B-Width-Base

SGLang

How to use nvidia/Llama-3.1-Minitron-4B-Width-Base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "nvidia/Llama-3.1-Minitron-4B-Width-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Llama-3.1-Minitron-4B-Width-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "nvidia/Llama-3.1-Minitron-4B-Width-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Llama-3.1-Minitron-4B-Width-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nvidia/Llama-3.1-Minitron-4B-Width-Base with Docker Model Runner:
```
docker model run hf.co/nvidia/Llama-3.1-Minitron-4B-Width-Base
```

Fixing typo at model_path param

by Dimitre - opened Aug 17, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+157

-157

Dimitre

Aug 17, 2024

No description provided.

Fixing type at model_path param46f3e703

Dimitre changed pull request title from Fixing type at model_path param to Fixing typo at model_path param Aug 17, 2024

Dimitre

Aug 17, 2024

•

edited Aug 17, 2024

I am not sure why the git diff points to all text but I only changed the value of model_path to fix a typo that was pointing to the wrong model

previously

model_path = "nvidia/Llama3.1-Minitron-4B-Width-Base"

correct

model_path = "nvidia/Llama-3.1-Minitron-4B-Width-Base"

KenanZeynalov

Aug 17, 2024

Thank you so much for finding this error. I was receiving for one hour that model is not recognized even though I pulled and fetched. I was gonna lose my mind. Props to you!!

srvm

NVIDIA org Aug 22, 2024

Thank you for noticing this. @Dimitre could you please update the PR with the latest README version? I'll merge it.

srvm

NVIDIA org Aug 22, 2024

Fixed in this commit. Thanks again! Closing.

srvm changed pull request status to closed Aug 22, 2024

Dimitre

Aug 24, 2024

My pleasure, thanks!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment