Instructions to use meta-llama/Meta-Llama-3-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Meta-Llama-3-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Meta-Llama-3-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Meta-Llama-3-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Meta-Llama-3-8B-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/Meta-Llama-3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meta-llama/Meta-Llama-3-8B-Instruct

SGLang

How to use meta-llama/Meta-Llama-3-8B-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/Meta-Llama-3-8B-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/Meta-Llama-3-8B-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/Meta-Llama-3-8B-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/Meta-Llama-3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meta-llama/Meta-Llama-3-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/meta-llama/Meta-Llama-3-8B-Instruct
```

Error while deserializing header: HeaderTooLarge

#123

by sbruhat - opened May 24, 2024

Discussion

sbruhat

May 24, 2024

Hi,

When I run python3 convert-hf-to-gguf.py ../Meta-Llama-3-8B-Instruct I get this errror "safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge"

I am using Python 3.11.9

Any idea what's going on? Thanks

sbruhat

May 27, 2024

•

edited May 27, 2024

I found the problem, the model I downloaded was incomplete.
I used git clone https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct without installing git lfs first.
So I ran git lfs install and the git clone https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct and it worked

osanseviero changed discussion status to closed May 29, 2024

ijkeleher

Jun 14, 2024

Also had this issue had to do a few more steps from @sbruhat 's solution

I had forgotten to install git-lfs

brew install git-lfs

I had to init lfs after installing

git install lfs

had to delete my model and then redownload, still had to use git lfs clone instead of git clone

rm -rf Meta-Llama-3-8B-Instruct
git lfs clone https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct

then i had a weird issue that was causing the DL to hang: warning: Multiple 'url.*..insteadof' keys with the same alias: "https://github.com/" so had to go into my .gitconfig and delete multiple git url insteadOf redirects.
finally i was able to run the convert script

python llama.cpp/convert-hf-to-gguf.py Meta-Llama-3-8B-Instruct/

2010b9

Feb 24, 2025

I had the same problem with another model from the Hub. Thanks for the solution.
However, shouldn't this be more transparent? In my case I was using a VM and had no git lfs installed. Shouldn't it throw an error or warning when downloading the model?

chio4696

Sep 17, 2025

For my fellow linux users:

curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash
sudo apt install git-lfs
git-lfs https://huggingface.co/{model name as always}

All good then.

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