Update README.md

README.md

@@ -16,27 +16,6 @@ pinned: false
 | [**Reference docs**](https://easydel.readthedocs.io/en/latest/)
 | [**License**](https://github.com/erfanzar/EasyDeL?tab=readme-ov-file#license-)
 
-EasyDeL is an open-source framework designed to enhance and streamline the training process of machine learning models, with a primary focus on Jax/Flax. It provides convenient and effective solutions for training and serving Flax/Jax models on TPU/GPU at scale.
-
-## Key Features
-
-- **Diverse Architecture Support**: Seamlessly work with various model architectures including Transformers, Mamba, RWKV, and more.
-- **Custom Kernels**: EasyDeL supports custom kernels and operation for both GPU (via mosaic and triton) and TPU (via pallas).
-- **Diverse Model Support**: Implements a wide range of models in JAX, including Falcon, Qwen2, Phi2, Mixtral, Qwen2Moe, Cohere, Dbrx, Phi3, and MPT.
-- **Advanced Trainers**: Offers specialized trainers like DPOTrainer, ORPOTrainer, SFTTrainer, and VideoCLM Trainer.
-- **Serving and API Engines**: Provides engines for efficiently serving large language models (LLMs) in JAX.
-- **Quantization and Bit Operations**: Supports various quantization methods and 8, 6, and 4-bit operations for optimized inference and training.
-- **Performance Optimization**: Integrates FlashAttention, RingAttention, and other performance-enhancing features.
-- **Model Conversion**: Supports automatic conversion between JAX-EasyDeL and PyTorch-HF models.
-
-### Fully Customizable and Hackable 🛠️
-
-EasyDeL stands out by providing unparalleled flexibility and transparency:
-
-- **Open Architecture**: Every single component of EasyDeL is open for inspection, modification, and customization. There are no black boxes here.
-- **Hackability at Its Core**: We believe in giving you full control. Whether you want to tweak a small function or completely overhaul a training loop, EasyDeL lets you do it.
-- **Custom Code Access**: All custom implementations are readily available and well-documented, allowing you to understand, learn from, and modify the internals as needed.
-- **Encourage Experimentation**: We actively encourage users to experiment, extend, and improve upon the existing codebase. Your innovations could become the next big feature!
-- **Community-Driven Development**: Share your custom implementations and improvements with the community, fostering a collaborative environment for advancing ML research and development.
+EasyDeL is an open-source framework designed to enhance and streamline the training process of machine learning models, with a primary focus on JAX. It provides convenient and effective solutions for training and serving JAX models on TPU/GPU at scale.
 
 With EasyDeL, you're not constrained by rigid frameworks. Instead, you have a flexible, powerful toolkit that adapts to your needs, no matter how unique or specialized they may be. Whether you're conducting cutting-edge research or building production-ready ML systems, EasyDeL provides the freedom to innovate without limitations.