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
```

Slow API Calls in Transformers

#98

by Zifeng01code - opened May 9, 2024

Discussion

Zifeng01code

May 9, 2024

I've started using the official transformer code recommended for API calls, but I'm encountering an issue where each call takes a significantly long time to complete...

Has anyone else faced similar challenges? I want to use this pre-trained model for text generate. I'm looking for any advice or tips on how to optimize these API calls to reduce the response time. Are there settings within the transformer model that I should tweak, or is there a more efficient way to handle these operations?

Zifeng01code

May 9, 2024

This comment has been hidden

HamzaYslmn

May 19, 2024

ı use ollama, best for usage.

bagmeet

Jul 2, 2024

Hi @HamzaYslmn - could you please share code snippet (or link to an example) for using ollama with llama-3?

HamzaYslmn

Jul 2, 2024

Hi @HamzaYslmn - could you please share code snippet (or link to an example) for using ollama with llama-3?

import ollama

ollama_response = ollama.chat(
    model='llama3',
    stream=True,
    messages=[
        {
            'role': 'system',
            'content': '''Respond fully in Turkish. Just Turkish, don't use another language. You are an assistant with solid philosophical knowledge.''',
        },
        {
            'role': 'user',
            'content': 'hayatın anlamı sence nedir?',
        },
    ]
)

for chunk in ollama_response:
    print(chunk['message']['content'], end='', flush=True)

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