Update README.md

README.md

@@ -4,57 +4,31 @@ datasets: eyad-silx/Quasar-Max-3.3
 library_name: transformers
 model_name: Quasar-3.0-Max
 tags:
-- generated_from_trainer
-- open-r1
+- rl 
+- silx
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for Quasar-3.0-Max
+# Quasar Series of Models
 
-This model is a fine-tuned version of [eyad-silx/Quasar-3.0-Max](https://huggingface.co/eyad-silx/Quasar-3.0-Max) on the [eyad-silx/Quasar-Max-3.3](https://huggingface.co/datasets/eyad-silx/Quasar-Max-3.3) dataset.
-It has been trained using [TRL](https://github.com/huggingface/trl).
+<p align="center">
+  <img src="https://pbs.twimg.com/media/GlaGzuIWcAAI1JO?format=png&name=small" alt="Quasar Model Image">
+</p>
 
-## Quick start
+## Introducing Quasar-3.3-Max
 
-```python
-from transformers import pipeline
+This model is provided by **SILX INC**. It has been supervised fine-tuned using the **open-r1** repository. The training data includes sequences of varying lengths (32k, 16k, and 8k) to enhance the model's knowledge and adaptability. 
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="silx-ai/Quasar-3.0-Max", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+Quasar-3.3-Max represents the **first step** in the Quasar project before Reinforcement Learning (RL). At this stage, the model's reasoning steps are capped at a **maximum length of 8129 tokens** to optimize processing efficiency and contextual understanding.
 
-## Training procedure
+Stay tuned for further updates as we advance the Quasar project with RL enhancements!
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mentoxcompuny-silx-ai/huggingface/runs/wmstn4dn) 
+## Resources
+- [Research Paper](https://arxiv.org/abs/2412.06822)
+- [Website](https://sicopilot.cloud)
 
-
-This model was trained with SFT.
-
-### Framework versions
-
-- TRL: 0.16.0.dev0
-- Transformers: 4.49.0
-- Pytorch: 2.5.1
-- Datasets: 3.3.2
-- Tokenizers: 0.21.0
-
-## Citations
-
-
-
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```
+## Founders
+- **Eyad Gomaa**
+- **Gomaa Salah**