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

Libraries

How to use meta-llama/Meta-Llama-3-8B 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")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use meta-llama/Meta-Llama-3-8B 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"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Meta-Llama-3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use meta-llama/Meta-Llama-3-8B 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" \
    --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": "meta-llama/Meta-Llama-3-8B",
		"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 "meta-llama/Meta-Llama-3-8B" \
        --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": "meta-llama/Meta-Llama-3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Error with Anaconda with Pycharm

#205

by yiwens - opened Jul 16, 2024

Discussion

yiwens

Jul 16, 2024

Hi,

I'm running Pycharm with the conda interpreter, and I have cuda installed and working properly. In the conda environment I installed pytorch, huggingface accelerate, and transformers packages. And my access token works as well.

Then I try to run the default example that's on the https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct page, and I'm getting an error saying
File "C:\Users\ethan\anaconda3\envs\CUDA\Lib\site-packages\transformers\pipelines\text_generation.py", line 233, in preprocess
prefix + prompt_text,
~~~~~~~^~~~~~~~~~~~~
TypeError: can only concatenate str (not "dict") to str

Can anyone help?

Thanks,
Ethan

Zery

Jul 19, 2024

tpadhi1

Jul 30, 2024

model_id = "meta-llama/Meta-Llama-3-8B-Instruct"

pipe = pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device=0,  # 'cuda' for GPU, 'cpu' for CPU
)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

# Combine messages into a single string prompt
prompt = "\n".join([f"{msg['role']}: {msg['content']}" for msg in messages])

# Get the EOS token ID
eos_token_id = pipe.tokenizer.eos_token_id

outputs = pipe(
    prompt,
    max_new_tokens=256,
    eos_token_id=eos_token_id,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)

assistant_response = outputs[0]["generated_text"]
print(assistant_response)

could you please try the above code?

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