# Anthony Assi: Open-Weight Models and Datasets
Source: https://savrn.com/model-publishers/assix-research
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Models

Model · Text generation

### [lebanese-llama-3.1-8b](https://savrn.com/models/lebanese-llama-3-1-8b)

[Anthony Assi](https://savrn.com/model-publishers/assix-research)

Lebanese-Llama-3.1-8B is a high-performance LLM fine-tuned specifically for the Lebanese dialect (Ammiya). It bridges the gap between Modern Standard Arabic (MSA) and the multi-modal nature of Lebanese communication, seamlessly blending Arabic script, French/English influences, and Arabizi (Romanized Arabic with numbers). This model was trained and validated on the NVIDIA DGX Spark, the world’s first personal AI supercomputer powered by the Grace Blackwell (GB10) architecture. Try the model instantly in your browser without any setup: To get the most authentic "Ammiya" experience, use this system prompt. It activates the model's specialized cultural knowledge and linguistic patterns. Speak…

Open weights mit 8B parameters 131,072 tokens transformers

[View model](https://savrn.com/models/lebanese-llama-3-1-8b)

Model · Text classification

### [SourceCodeAuthorCheck-SLM-10M](https://savrn.com/models/sourcecodeauthorcheck-slm-10m)

[Anthony Assi](https://savrn.com/model-publishers/assix-research)

A ~10 million parameter Small Language Model (SLM) Transformer designed for binary classification to detect whether Python source code was written by a human or generated by AI. The model was trained on a dataset of human-written code extracted from GitHub (Q3 2017 and prior) and synthetic AI-generated code mimicking Q3 2026 generative AI paradigms. You can test the model interactively without writing any code by visiting our Gradio Web UI Space. To use this model locally, you must include the model architecture class in your script before loading the weights. Once the class is defined, you can automatically pull the weights from Hugging Face and run inference cleanly using this helper…

Open weights mit

[View model](https://savrn.com/models/sourcecodeauthorcheck-slm-10m)

## Explore More

- [All model publishers](https://savrn.com/model-publishers)
- [The model directory](https://savrn.com/models)
- [The dataset directory](https://savrn.com/datasets)

## Source

- Listed from their public repositories, read 2026-10-02.
- [Hugging Face profile](https://huggingface.co/assix-research)
- [How the hub is built](https://savrn.com/model-hub/methodology)