Update README.md

README.md

@@ -44,26 +44,18 @@ To ensure the robustness and effectiveness of Llama-3-SEC, the model has undergo
 
 - Domain-specific perplexity, measuring the model's performance on SEC-related data
 
-![Domain Specific Perplexity of Model Variants](https://i.ibb.co/xGHRfLf/Screenshot-2024-06-11-at-10-23-59-PM.png){width=400}
+<img src="https://i.ibb.co/xGHRfLf/Screenshot-2024-06-11-at-10-23-59-PM.png" width="400">
 
 - Extractive numerical reasoning tasks, using subsets of TAT-QA and ConvFinQA datasets
 
-![Domain Specific Evaluations of Model Variants](https://i.ibb.co/2v6PdDx/Screenshot-2024-06-11-at-10-25-03-PM.png){width=400}
+<img src="https://i.ibb.co/2v6PdDx/Screenshot-2024-06-11-at-10-25-03-PM.png" width="400">
 
 - General evaluation metrics, such as BIG-bench, AGIEval, GPT4all, and TruthfulQA, to assess the model's performance on a wide range of tasks
 
-![General Evaluations of Model Variants](https://i.ibb.co/K5d0wMh/Screenshot-2024-06-11-at-10-23-18-PM.png){width=600}
-
-- General perplexity on various datasets, including bigcode/starcoderdata, open-web-math/open-web-math, allenai/peS2o, mattymchen/refinedweb-3m, and Wikitext
+<img src="https://i.ibb.co/K5d0wMh/Screenshot-2024-06-11-at-10-23-18-PM.png" width="600">
 
 The evaluation results demonstrate significant improvements in domain-specific performance while maintaining strong general capabilities, thanks to the use of advanced CPT and model merging techniques.
 
-In this version:
-- The images are resized using the `{width=X}` syntax in Markdown, where `X` represents the desired width in pixels.
-- The first two images are set to a width of 400 pixels.
-- The last image is set to a width of 600 pixels.
-
-This approach keeps the original structure and text of the evaluation section while simply making the images smaller using Markdown syntax.
 
 ## Training and Inference