Instructions to use meta-llama/Llama-3.1-70B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-3.1-70B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-70B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-70B-Instruct")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-70B-Instruct")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Llama-3.1-70B-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-3.1-70B-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-3.1-70B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-3.1-70B-Instruct

SGLang

How to use meta-llama/Llama-3.1-70B-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-3.1-70B-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-3.1-70B-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-3.1-70B-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-3.1-70B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meta-llama/Llama-3.1-70B-Instruct with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-3.1-70B-Instruct
```

Context window size?

#23

by JulienGuy - opened Aug 13, 2024

Discussion

JulienGuy

Aug 13, 2024

Hello,

I am calling Meta-Llama-3.1-70B-Instruct using Haystack v2.0's HuggingFaceTGIGenerator in the context of a RAG application.

Although this model is advertised as having a 128k context window size, as opposed to Meta-Llama-3.1-70B-Instruct's 8k context window size, I get the following error:

I am puzzled as to whether this model's context window is purposefully limited to 8k token or if this is an issue of compatibility with Haystack 2.0? Any hints would be appreciated here.

Ixex1

Aug 16, 2024

Great Question. I also would like to know the answer.

JulienGuy

Aug 17, 2024

Hi Ixex1,

Turns out it's easy: you deploy the model on a (paid) dedicated inference endpoint and configure it to accept long inputs.

Ofc it means you're paying for the hardware you're renting.

Ixex1

Aug 19, 2024

Awesome! Thanks so much. Is there a link you could share? I'm unsure of where to begin....

JulienGuy

Aug 19, 2024

You go to your model card like here: https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct

And you click on "deploy" and "Inference Endpoint".

You will have a number of options to configure the endpoint.

If you need the higher end hardware like Nvidia A100, beware that HuggingFace may not be currently able to fulfill your needs as availability is limited. Contacting customer support can help.

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