Update README.md

README.md

@@ -6,13 +6,6 @@ datasets:
 - StanfordAIMI/interpret-cxr-test-hidden
 ---
 
-<Gallery />
-
-widget:
-- text: "drawing of tintin in a shop"
-  output:
-    url: "tokens.drawio.png"
-
 # CXRMate-RRG4: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation
 
 This is an evolution of https://huggingface.co/aehrc/cxrmate developed for the Radiology Report Generation task of BioNLP @ ACL 2024.
@@ -25,7 +18,7 @@ For this, we proposed EAST: Entropy-Augmented Self-critical sequence Training (E
 
 EAST was applied to a multimodal language model with RadGraph as the reward. Other features include:
  - Token type embeddings to differentiate between findings and impression section tokens, as well as image embeddings. 
- - Special tokens (`NF` and `NI`) to handle missing *findings* and *impression* sections. 
+ - Special tokens (`[NF]` and `[NI]`) to handle missing *findings* and *impression* sections. 
  - Non-causal attention masking for the image embeddings and a causal attention masking for the report token embeddings.
 
 ## Example: