Instructions to use FloatingDuck/zoom_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FloatingDuck/zoom_model with Transformers:

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

pipe = pipeline("text-generation", model="FloatingDuck/zoom_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("FloatingDuck/zoom_model")
model = AutoModelForMultimodalLM.from_pretrained("FloatingDuck/zoom_model")
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 FloatingDuck/zoom_model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FloatingDuck/zoom_model

SGLang

How to use FloatingDuck/zoom_model 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 "FloatingDuck/zoom_model" \
    --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": "FloatingDuck/zoom_model",
		"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 "FloatingDuck/zoom_model" \
        --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": "FloatingDuck/zoom_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use FloatingDuck/zoom_model with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for FloatingDuck/zoom_model to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for FloatingDuck/zoom_model to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FloatingDuck/zoom_model to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="FloatingDuck/zoom_model",
    max_seq_length=2048,
)

Docker Model Runner
How to use FloatingDuck/zoom_model with Docker Model Runner:
```
docker model run hf.co/FloatingDuck/zoom_model
```

Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms "Typo" Correction

Model Overview

This is a fine-tuned version of the LLaMA-3.2-3B model for Acoustic Side-Channel Attacks (ASCA), designed to improve keystroke classification and error correction in noisy environments. The model leverages Vision Transformers (VTs) for spectrogram classification and Large Language Models (LLMs) for typo correction.

Fine-Tuned From: unsloth/llama-3.2-3b-instruct-bnb-4bit
License: CC
Developed by: Seyyed Ali Ayati, Jin Hyun Park, Yichen Cai, Marcus Botacin
Repository: EchoCrypt GitHub

Citation

If you use this model, please cite the following paper:

@article{ayati2025making,
  title={Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms' "Typo" Correction},
  author={Ayati, Seyyed Ali and Park, Jin Hyun and Cai, Yichen and Botacin, Marcus},
  journal={arXiv preprint arXiv:2504.11622},
  year={2025},
  url={https://arxiv.org/abs/2504.11622}
}

Downloads last month: 6

Paper for FloatingDuck/zoom_model

Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms' "Typo" Correction

Paper • 2504.11622 • Published Apr 15, 2025