Instructions to use meta-llama/Llama-3.1-405B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-3.1-405B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-405B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-405B-Instruct")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-405B-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Llama-3.1-405B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-3.1-405B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.1-405B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-3.1-405B-Instruct

SGLang

How to use meta-llama/Llama-3.1-405B-Instruct 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 "meta-llama/Llama-3.1-405B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.1-405B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "meta-llama/Llama-3.1-405B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Llama-3.1-405B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meta-llama/Llama-3.1-405B-Instruct with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-3.1-405B-Instruct
```

Please move PTH/original into new model/repo.

by Qubitium - opened Jul 23, 2024

Discussion

Qubitium

Jul 23, 2024

Having the original pth files double the bandwidth cost and time. Please move the original pth to a separate model/repo. Thank you! I can image the 405B downloaders having a tough time syncing a 2TB repo.

uralik

Jul 23, 2024

Having the original pth files double the bandwidth cost and time. Please move the original pth to a separate model/repo. Thank you! I can image the 405B downloaders having a tough time syncing a 2TB repo.

as a workaround you can initialize the model using transformers code, this way it will only pull safetensors instead of the entire repo

tsmswifty

Jul 24, 2024

if you don't want to use transformers, clone with git lfs with pointers and run this: git lfs pull --include "*.safetensors"

note that it will still take more space than the size of the safetensors alone, but it will not consume more bandwidth

Qubitium

Jul 24, 2024

huggingface-cli download --exclude="*original*" does the trick

JohnnieB

Aug 2, 2024

•

edited Aug 4, 2024

Can we delete the hidden .git file once we've downloaded the model?

xujfcn

Feb 24

If you're looking for an easy way to access this model via API, you can use Crazyrouter — it provides an OpenAI-compatible endpoint for 600+ models including this one. Just pip install openai and change the base URL.

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