upgrade images

README.md

@@ -7,12 +7,11 @@ tags:
     - multilingual-code-generation
 ---
 
-# CodeUp: A Multilingual Code Generation Llama2 Model with Parameter-Efficient Instruction-Tuning on a Single RTX 3090
-
 <!-- <p align="center" width="70%">
 <img src="assets/Logo.jpg" alt="HKUST CodeUp" style="width: 50%; min-width: 250px; display: block; margin: auto;">
 </p> -->
 ![HKUST CodeUp](assets/Logo.jpg)
+# CodeUp: A Multilingual Code Generation Llama2 Model with Parameter-Efficient Instruction-Tuning on a Single RTX 3090
 
 ## Description
 In recent years, large language models (LLMs) have shown exceptional capabilities in a wide range of applications due to their fantastic emergence ability. To align with human preference, instruction-tuning and reinforcement learning from human feedback (RLHF) are proposed for Chat-based LLMs (e.g., ChatGPT, GPT-4). However, these LLMs (except for Codex) primarily focus on the general domain and are not specifically designed for the code domain. Although Codex provides an alternative choice, it is a closed-source model developed by OpenAI. Hence, it is imperative to develop open-source instruction-following LLMs for the code domain. 
@@ -45,11 +44,7 @@ This way, we gain the 19K high-quality instruction data of code generation. The
 | -- | -- |
 | <center><img src="assets/PL_Raw.png" width="100%"></center>  | <center><img src="assets/PL_Clean.png" width="92%"></center> |  -->
 
-**Raw Data (20K + 4K)**
-![Raw Data (20K + 4K)](assets/PL_Raw.png)
-
-**Filtered Data (19K)**
-![Filtered Data (19K)](assets/PL_Clean.png)
+![PL Data Filtering)](assets/PL_Filter.jpg)
 
 
 ## Training & Inference