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

Libraries

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

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

pipe = pipeline("text-generation", model="NousResearch/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("NousResearch/Meta-Llama-3-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Meta-Llama-3-8B-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
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

fix eoi_id token?

by mradermacher - opened Apr 19, 2024

Discussion

mradermacher

Apr 19, 2024

Hi!

are you planning to fix the tokenizer config (see https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct-GGUF/discussions/2 )? I don't know what the actual llama-3 repo does.

3Simplex

Apr 19, 2024

•

edited Apr 19, 2024

Hi!

are you planning to fix the tokenizer config (see https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct-GGUF/discussions/2 )? I don't know what the actual llama-3 repo does.

I read there are a few PRs in llama.cpp to adapt the way llama3 uses bpe tokens.
I just did this quick hacky fix I found I don't expect this is a real solution though.

Problem: Llama-3 uses 2 different stop tokens, but llama.cpp only has support for one.
The reason that the <|end_of-text|> did not work is a llama.cpp thing, I see some guys working to add support now.

Maybe this is irrelevant now... I did this before they updated the template today.

mradermacher

Apr 20, 2024

I think now the fix isn't a fix, and this is just a new model feature that llama.cpp doesn't handle.

mradermacher changed discussion status to closed Apr 20, 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