Instructions to use uchihamadara1816/Multi-Learned-Deepfake-Det with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uchihamadara1816/Multi-Learned-Deepfake-Det with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="uchihamadara1816/Multi-Learned-Deepfake-Det",
	filename="mobilevlm.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use uchihamadara1816/Multi-Learned-Deepfake-Det with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf uchihamadara1816/Multi-Learned-Deepfake-Det
# Run inference directly in the terminal:
llama-cli -hf uchihamadara1816/Multi-Learned-Deepfake-Det

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf uchihamadara1816/Multi-Learned-Deepfake-Det
# Run inference directly in the terminal:
llama-cli -hf uchihamadara1816/Multi-Learned-Deepfake-Det

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf uchihamadara1816/Multi-Learned-Deepfake-Det
# Run inference directly in the terminal:
./llama-cli -hf uchihamadara1816/Multi-Learned-Deepfake-Det

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf uchihamadara1816/Multi-Learned-Deepfake-Det
# Run inference directly in the terminal:
./build/bin/llama-cli -hf uchihamadara1816/Multi-Learned-Deepfake-Det

Use Docker

docker model run hf.co/uchihamadara1816/Multi-Learned-Deepfake-Det

LM Studio
Jan
Ollama
How to use uchihamadara1816/Multi-Learned-Deepfake-Det with Ollama:
```
ollama run hf.co/uchihamadara1816/Multi-Learned-Deepfake-Det
```

Unsloth Studio new

How to use uchihamadara1816/Multi-Learned-Deepfake-Det 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 uchihamadara1816/Multi-Learned-Deepfake-Det 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 uchihamadara1816/Multi-Learned-Deepfake-Det to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for uchihamadara1816/Multi-Learned-Deepfake-Det to start chatting

Docker Model Runner
How to use uchihamadara1816/Multi-Learned-Deepfake-Det with Docker Model Runner:
```
docker model run hf.co/uchihamadara1816/Multi-Learned-Deepfake-Det
```

Lemonade

How to use uchihamadara1816/Multi-Learned-Deepfake-Det with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull uchihamadara1816/Multi-Learned-Deepfake-Det

Run and chat with the model

lemonade run user.Multi-Learned-Deepfake-Det-{{QUANT_TAG}}

List all available models

lemonade list

🧠 Deepfake Reasoning with MobileVLM

Multimodal deepfake analysis using MobileVLM for human-readable forensics.

🚀 Overview

This system implements a multimodal reasoning pipeline for deepfake detection. Unlike traditional "black-box" classifiers, this system generates natural language explanations by bridging visual features with generative language modeling — making forensic results interpretable and actionable.

🏗️ Architecture & Pipeline

Multimodal Reasoning Flow

Input Image → CLIP Vision Encoder → Adapter Network → Multimodal Projector → MobileVLM → Final Explanation

System Components

Component	Role	Specification
CLIP Encoder	Visual Backbone	Frozen ViT weights
Adapter	Refinement	Trainable MLP (1024→512→1024)
Projector	Alignment	Linear mapping to LLM space
MobileVLM	Reasoning	Generates textual forensics

💡 Example Output

"This image is classified as Fake. Forensic analysis reveals inconsistent lighting
gradients on the subject's face and blurred texture artifacts along the jawline,
typical of GAN-based generation."

📊 Final Performance Metrics

Our "Deepfake-Aware" calibration of the vision-to-language projector has achieved industry-leading results for mobile-first models:

Target Set	Accuracy / Achievement
Celeb-DF-v2 (Videos)	96.76% FAKE Detection
Unified Image Test Set	94.20% Accuracy
Inference Latency	< 2s per frame (on Mobile NPU)
Memory Efficiency	~2.6GB Footprint (Q4_K_M)

📦 Installation & Usage

1. Clone the Repository

git clone https://github.com/your-repo/mobilevlm-deepfake
cd mobilevlm-deepfake

2. Install Dependencies

pip install -r requirements.txt

3. Run Inference

# Extract features and refine
feats = vision_tower(image)
cls_feat = adapter(feats[:, 0])
feats[:, 0] = cls_feat

# Project and Generate
projected_feats = projector(feats)
output = model.generate(projected_feats, prompt="Analyze forgery")

🗺️ Roadmap

On-Device Reasoning — Porting the full stack to mobile NPUs
Enhanced Projectors — Implementing Q-Formers for alignment
Expanded Datasets — Adding Diffusion-based forgery samples

👤 Author

Sai Kamal Nannuri
AI & Machine Learning Researcher | Computer Vision Specialist

Downloads last month: 175

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support