Update transparent main for webpage

docs/index.html

@@ -166,7 +166,7 @@ <h1 class="title is-1 publication-title">
         <h3 class="subtitle is-size-3-tablet has-text-left pb-">
 
             <p style="text-align:justify; line-height:150%; margin-left: -75px; margin-right: -75px; font-size: 20px">
-                <img src="static/images/main.png"/>
+                <img src="static/images/main_transparent.png"/>
 
                 <br><br>
                 Large language models (LLMs) have established great success in the general domain of natural language processing. Their emerging task generalization and free-form dialogue capabilities can greatly help to design <b>Chemical General Intelligence (CGI)</b> to assist real-world research in chemistry. However, the existence of specialized language and knowledge in the field of chemistry, such as the highly informative SMILES notation, hinders the performance of general-domain LLMs in chemistry. To this end, we develop <b>ChemDFM</b>, the first LLM towards CGI. ChemDFM-13B is trained on 34B tokens from chemical literature, textbooks, and instructions as well as various data from the general domain. <i>Therefore, it can store, understand, and reason over chemical knowledge and languages while still possessing advanced free-form language comprehension capabilities.</i> Extensive quantitative evaluation shows that ChemDFM can <i>significantly outperform the representative open-sourced LLMs</i>. Moreover, ChemDFM can also <i>surpass GPT-4 on a great portion of chemical tasks, despite the significant size difference</i>. Further qualitative evaluations demonstrate the efficiency and effectiveness of ChemDFM in real-world research scenarios.