Instructions to use Vira21/Llama-3.2-3B-Instruct-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vira21/Llama-3.2-3B-Instruct-adapter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "Vira21/Llama-3.2-3B-Instruct-adapter")

Transformers

How to use Vira21/Llama-3.2-3B-Instruct-adapter with Transformers:

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

pipe = pipeline("text-generation", model="Vira21/Llama-3.2-3B-Instruct-adapter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Vira21/Llama-3.2-3B-Instruct-adapter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Vira21/Llama-3.2-3B-Instruct-adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vira21/Llama-3.2-3B-Instruct-adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vira21/Llama-3.2-3B-Instruct-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Vira21/Llama-3.2-3B-Instruct-adapter

SGLang

How to use Vira21/Llama-3.2-3B-Instruct-adapter 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 "Vira21/Llama-3.2-3B-Instruct-adapter" \
    --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": "Vira21/Llama-3.2-3B-Instruct-adapter",
		"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 "Vira21/Llama-3.2-3B-Instruct-adapter" \
        --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": "Vira21/Llama-3.2-3B-Instruct-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Vira21/Llama-3.2-3B-Instruct-adapter with Docker Model Runner:
```
docker model run hf.co/Vira21/Llama-3.2-3B-Instruct-adapter
```

Llama-3.2-3B-Instruct-adapter / tokenizer.json

Vira21

Upload 7 files

9c66a47 verified about 1 year ago

History Blame Contribute Delete

17.2 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 9c5154a25b9c0f98513e9de0b85f31bb167bdea6402bcc1c73a78011a8036308
Size of remote file:: 17.2 MB
SHA256:: 32ed7bccc082eb6c2b2ab677e0f5bf97db02992c28d186fe370239bc7737c35a

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.