Instructions to use mahmoudalyosify/Horus-OSINT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use mahmoudalyosify/Horus-OSINT with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mahmoudalyosify/Horus-OSINT:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mahmoudalyosify/Horus-OSINT:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mahmoudalyosify/Horus-OSINT:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mahmoudalyosify/Horus-OSINT:Q4_K_M

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 mahmoudalyosify/Horus-OSINT:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mahmoudalyosify/Horus-OSINT:Q4_K_M

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 mahmoudalyosify/Horus-OSINT:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mahmoudalyosify/Horus-OSINT:Q4_K_M

Use Docker

docker model run hf.co/mahmoudalyosify/Horus-OSINT:Q4_K_M

LM Studio
Jan

vLLM

How to use mahmoudalyosify/Horus-OSINT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mahmoudalyosify/Horus-OSINT:Q4_K_M

Ollama
How to use mahmoudalyosify/Horus-OSINT with Ollama:
```
ollama run hf.co/mahmoudalyosify/Horus-OSINT:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use mahmoudalyosify/Horus-OSINT with Docker Model Runner:
```
docker model run hf.co/mahmoudalyosify/Horus-OSINT:Q4_K_M
```

Lemonade

How to use mahmoudalyosify/Horus-OSINT with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mahmoudalyosify/Horus-OSINT:Q4_K_M

Run and chat with the model

lemonade run user.Horus-OSINT-Q4_K_M

List all available models

lemonade list

Atomic Chat

mahmoudalyosify commited on Apr 22

Commit

3c1cefb

verified ·

1 Parent(s): 0ed982b

Update README.md

Browse files

Files changed (1) hide show

README.md +26 -0

README.md CHANGED Viewed

@@ -1,3 +1,29 @@
 # 🦅 Horus-OSINT
 A Cloud-Based Conversational Chatbot for Open-Source Intelligence (OSINT) and Global Threat Analysis using Fine-Tuned Lightweight LLMs.

+---
+license: apache-2.0
+library_name: unsloth
+base_model: unsloth/Meta-Llama-3-8B-Instruct-bnb-4bit
+tags:
+- llm
+- llama-3
+- osint
+- threat-intelligence
+- quantization
+- gguf
+- ollama
+- geopolitics
+- academic-project
+pipeline_tag: text-generation
+datasets:
+- GTD
+- GDELT
+model_creator:
+- Mahmoud Alyosify
+- Sondos Omar
+- Mirna Embaby
+language:
+- en
+---
 # 🦅 Horus-OSINT
 A Cloud-Based Conversational Chatbot for Open-Source Intelligence (OSINT) and Global Threat Analysis using Fine-Tuned Lightweight LLMs.