Upload folder using huggingface_hub

README.md

@@ -46,7 +46,6 @@ Solidity-Code-LLM is a specialized language model trained in two stages: pre-tra
 
 ### Model Sources
 For more details, please refer to,
-- **Paper [optional]:** {{ paper | default("[More Information Needed]", true)}}
 - **Demo:** [Demo On Hugging Face Space](https://huggingface.co/spaces/Chain-GPT/SolidityLLMDemo)
 
 
@@ -64,8 +63,12 @@ On the following parameters
 - Security(%)--Percentage of code free from common vulnerabilities detected by Slither.
 
 ## Benchmark
-The figure below presents a detailed comparison of the models across all evaluation criteria
+Below is a figure summarizing the performance of each model across the four evaluation metrics.
 ![Benchmark](Benchmark.png)
+- Solidity LLM consistently achieved the highest compilation success rate.
+- It frequently adhered to OpenZeppelin standards, using appropriate imports and contract structures.
+- The contracts it produced were gas-efficient, as identified by Slither's optimization suggestions.
+- While some security vulnerabilities were detected, the overall security posture was acceptable, and the code quality remained high.
 
 
 # Uses