Instructions to use meta-llama/Llama-3.2-1B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-3.2-1B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Llama-3.2-1B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Llama-3.2-1B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-3.2-1B-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/Llama-3.2-1B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-3.2-1B-Instruct

SGLang

How to use meta-llama/Llama-3.2-1B-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/Llama-3.2-1B-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/Llama-3.2-1B-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/Llama-3.2-1B-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/Llama-3.2-1B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meta-llama/Llama-3.2-1B-Instruct with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-3.2-1B-Instruct
```

Display_Prompt = no

#24

by thegamecat - opened Oct 15, 2024

Discussion

thegamecat

Oct 15, 2024

My understanding is this parameter should suppress the output of the Prompt. It appears to do nothing, or I'm putting it in the wrong place. Anyone know how to use it?

Sanyam

Oct 16, 2024

Can you share more details please?

thegamecat

Oct 16, 2024

Basically the prompt is always appearing in the output from the LLM.

Happens with both 1b and 3b instruct.

I am not using pipeline.

It happens whether I use a chat template / system, user approach or not.

I can share some code tomorrow if that helps. I'm basically looking for a parameter to just get the response displayed.

codelion

Oct 29, 2024

@thegamecat just split the output upto input length and take the rest as response:

response = tokenizer.decode(output[0][len(inputs[0]):])

thegamecat

Nov 14, 2024

The number of tokens is already exceeded by that point.

codelion

Nov 14, 2024

What do you mean exceeded? Just increase the max_new_tokens to a larger value 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