Instructions to use meta-llama/Llama-3.2-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-3.2-3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Llama-3.2-3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-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/Llama-3.2-3B-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-3.2-3B-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-3.2-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-3.2-3B-Instruct

SGLang

How to use meta-llama/Llama-3.2-3B-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-3.2-3B-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-3.2-3B-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-3.2-3B-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-3.2-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meta-llama/Llama-3.2-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-3.2-3B-Instruct
```

I keep receiving 503 error when using HuggingFaceEndpoint to access the model

#154

by CinderLord - opened Apr 20, 2025

Discussion

CinderLord

Apr 20, 2025

Here're my codes:

import os
import warnings
from urllib3.exceptions import NotOpenSSLWarning
from langchain_huggingface import HuggingFaceEndpoint
import sys

warnings.filterwarnings("ignore", category=NotOpenSSLWarning)
os.environ["HUGGINGFACEHUB_API_TOKEN"] = '....'
llm = HuggingFaceEndpoint(
repo_id="meta-llama/Llama-3.2-3B-Instruct",
timeout=60
)

def explain_code(code):
base_prompt = """
Tell me about the flower
"""
prompt = base_prompt + code
completion = llm.invoke(prompt)
return completion

if name == "main":
code = """rose"""
result = explain_code(code)
print(result)

But I got the error as follows:

raise HTTPError(http_error_msg, response=self)

requests.exceptions.HTTPError: 503 Server Error: Service Temporarily Unavailable for url: https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.2-3B-Instruct

Please could someone tell me how to fix the problem?
Thanks!!!

CinderLord changed discussion title from Why I keep receiving 503 error when using HuggingFaceEndpoint to access the model? to Why I kept receiving 503 error when using HuggingFaceEndpoint to access the model? Apr 20, 2025

CinderLord changed discussion title from Why I kept receiving 503 error when using HuggingFaceEndpoint to access the model? to I keep receiving 503 error when using HuggingFaceEndpoint to access the model? Apr 20, 2025

CinderLord changed discussion title from I keep receiving 503 error when using HuggingFaceEndpoint to access the model? to I keep receiving 503 error when using HuggingFaceEndpoint to access the model Apr 20, 2025