plagonx69

Plagon X 69 LLM

Plagon X 69 is a custom Large Language Model (LLM) developed by Shehab, optimized for real-time performance on local hardware (like the AMD Ryzen 5 5600GT). It is based on the GPT-2 architecture but customized for specific conversational tasks.

🚀 Model Details

• Architecture: GPT-2 (Customized)
• Parameters: ~124 Million
• Optimization: FP32 (SafeTensors) & TFLite (8-bit Quantized)
• Developer: Shehab

🛠️ Intended Use

This model is designed for interactive chat applications and local AI experimentation. It is lightweight enough to run on mid-range CPUs and integrated GPUs without significant lag.

💻 How to Run Locally

You can use the plagon_web.py script to launch a web-based interface for this model.

from transformers import GPT2LMHeadModel, GPT2Tokenizer

model_id = "sbshehab200/plagonx69"
tokenizer = GPT2Tokenizer.from_pretrained(model_id)
model = GPT2LMHeadModel.from_pretrained(model_id)

# Example interaction
input_text = "Hello Plagon!"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

⚖️ License

This project is licensed under the MIT License.

---

Created with ❤️ by Shehab.