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
```

Is it really good?

#20

by urtuuuu - opened Apr 19, 2024

Discussion

urtuuuu

Apr 19, 2024

According to my tests, hermes 2 pro mistral 7b still wins. Tested on https://www.lsac.org/lsat/taking-lsat/test-format/logical-reasoning/logical-reasoning-sample-questions . And some other questions that i usually ask. I may be wrong, but that's what i got...

sirus

Apr 19, 2024

you can't really compare some extremely finetuned model like hermes 2 pro to a basic instruct finetune. I'm sure NousResearch will do their own instruct finetune of llama 3 8b and that is what you would compare. otherwise you could compare this llm to mistral instruct that's directly from mistral

aeminkocal

Apr 19, 2024

It's better than any of the models I tested before. And I tested A LOT. I believe Hermes etc. are trained to pass those tests. This model is actually the smartest one I've ever tested.

urtuuuu

Apr 19, 2024

you can't really compare some extremely finetuned model like hermes 2 pro to a basic instruct finetune. I'm sure NousResearch will do their own instruct finetune of llama 3 8b and that is what you would compare. otherwise you could compare this llm to mistral instruct that's directly from mistral

You are right, but I'm just a simple user, whichever model performs best, preferably lower in size, i use it and love it :)

97k

Apr 19, 2024

It is good. I put on a colab notebook and challenged Llama3-8B-instructioin model to extract entities from resume and also a chat-with-your resume Langchain chain.
It worked flawlessly!
Mistral-7B-instruct gave me hard time with entity extraction.

aak7912

Apr 19, 2024

•

edited Apr 19, 2024

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