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

Libraries

How to use TheAverageDetective/Llama-3.2-1B-Instruct-openvino with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheAverageDetective/Llama-3.2-1B-Instruct-openvino")
model = AutoModelForCausalLM.from_pretrained("TheAverageDetective/Llama-3.2-1B-Instruct-openvino", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheAverageDetective/Llama-3.2-1B-Instruct-openvino with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheAverageDetective/Llama-3.2-1B-Instruct-openvino"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheAverageDetective/Llama-3.2-1B-Instruct-openvino",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheAverageDetective/Llama-3.2-1B-Instruct-openvino

SGLang

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

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

This model was converted to OpenVINO from meta-llama/Llama-3.2-1B-Instruct using optimum-intel via the export space.

Install packages:

pip install optimum[openvino] transformers torch

Sample code:

from optimum.intel import OVModelForCausalLM
from transformers import AutoTokenizer

model_id = "TheAverageDetective/Llama-3.2-1B-Instruct-openvino"
model = OVModelForCausalLM.from_pretrained(model_id, device="GPU")
tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Explain the theory of relativity in simple terms."

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]

input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(input_text, return_tensors="pt")
output_ids = model.generate(**inputs, max_new_tokens=150)
result = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0]

print("\n", result)

Downloads last month: 21

Model tree for TheAverageDetective/Llama-3.2-1B-Instruct-openvino

Base model

meta-llama/Llama-3.2-1B-Instruct

Finetuned

(1804)

this model

Collection including TheAverageDetective/Llama-3.2-1B-Instruct-openvino

llamas

Collection

llama models in openvino format, converted using optimum • 2 items • Updated Mar 31