CHANGELOG angepasst.

CHANGELOG.md

@@ -4,31 +4,36 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](http://semver.org/).
 
-## [0.1.0] - 2024/08/04
 
-### Added
+## [0.3.4] - 2024/10/18
 
-- Initial commit
+### Updated
 
-## [0.2.0] - 2024/22/04
+- improved the hidden states generation method
+- project structure refactoring
 
-### Added
+## [0.3.3] - 2024/10/10
 
-- Conversion: Utilize **gba2mlx.py** to convert models from GBA format to a format compatible with the MLX framework, ensuring smooth integration and optimal performance.
-- Generation: Includes scripts for generating content using GBA quantized models within the MLX environment, empowering users to leverage the advanced capabilities of GBA models for natural language content creation.
-- Fully support [GreenBitAI's MLX Model Collection](https://huggingface.co/collections/GreenBitAI/greenbitai-mlx-llm-6614eb6ceb8da657c2b4ed58)
+### Added
 
-## [0.2.1] - 2024/01/05
+- langchain integration
+- local_rag and graph_rag example
 
-### Added
+### Updated
 
-- support for Phi-3
+- generate method to support hidden states output
 
-## [0.3.0] - 2024/11/06
+## [0.3.2] - 2024/09/09
 
 ### Added
 
-- Lora support for GBA low-bit models.
+- model management, FastAPI-server
+- unit test
+
+### Updated
+
+- synchronized with the mlx-lm
+- simplified README
 
 ## [0.3.1] - 2024/14/06
 
@@ -37,25 +42,28 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 - updated mlx_fastchat_worker for supporting mlx >= 0.14.
 - updated conda config.
 
-## [0.3.2] - 2024/09/09
+## [0.3.0] - 2024/11/06
 
 ### Added
 
-- model management, FastAPI-server
-- unit test
+- Lora support for GBA low-bit models.
 
-### Updated
+## [0.2.1] - 2024/01/05
 
-- synchronized with the mlx-lm
-- simplified README
+### Added
 
-## [0.3.3] - 2024/10/10
+- support for Phi-3
+
+## [0.2.0] - 2024/22/04
 
 ### Added
 
-- langchain integration
-- local_rag and graph_rag example
+- Conversion: Utilize **gba2mlx.py** to convert models from GBA format to a format compatible with the MLX framework, ensuring smooth integration and optimal performance.
+- Generation: Includes scripts for generating content using GBA quantized models within the MLX environment, empowering users to leverage the advanced capabilities of GBA models for natural language content creation.
+- Fully support [GreenBitAI's MLX Model Collection](https://huggingface.co/collections/GreenBitAI/greenbitai-mlx-llm-6614eb6ceb8da657c2b4ed58)
 
-### Updated
+## [0.1.0] - 2024/08/04
+
+### Added
 
-- generate method to support hidden states output
+- Initial commit