Update README.md

README.md

@@ -11,6 +11,7 @@ metrics:
 
 Logic2Vision is a [LLaVA-1.5-13B](https://huggingface.co/llava-hf/llava-1.5-13b-hf) model finetuned on [VisReas dataset](https://arxiv.org/abs/2403.10534) for complex visual reasoning tasks.
 
+![results](https://huggingface.co/RE-N-Y/logic2vision/resolve/main/Code2Vision.png)
 
 ## Model Details
 
@@ -81,7 +82,9 @@ processor.batch_decode(generate_ids, skip_special_tokens=True)
 
 ## Bias, Risks, and Limitations
 
-TBD
+The model has been mostly trained on VisReas dataset which is generated from [Visual Genome](https://homes.cs.washington.edu/~ranjay/visualgenome/index.html) dataset.
+Furthermore, since the VLM was mostly finetuned to solve visual reasoning tasks by "generating python pseudocode" outputs provided by the user. 
+Hence, it may struggle to adopt to different prompt styles and code formats.
 
 ## Training / Evaluation Details
 
@@ -90,7 +93,7 @@ LoRA modules were attached to `["q_proj", "v_proj"]`. We use DDP for distributed
 
 ### Results
 
-TBD
+![results](https://huggingface.co/RE-N-Y/logic2vision/resolve/main/results.png)
 
 ## Citation
 
@@ -108,4 +111,5 @@ TBD
 
 ## Model Card Authors
 
-TBD
+- Sangwu Lee - [Google Scholar](https://scholar.google.com/citations?user=FBJeGpAAAAAJ) - [Github](https://github.com/RE-N-Y) - [LinkedIn](https://www.linkedin.com/in/sangwulee/)
+- Syeda Akter - [Google Scholar](https://scholar.google.com/citations?hl=en&user=tZFFHYcAAAAJ) - [Github](https://github.com/snat1505027) - [LinkedIn](https://www.linkedin.com/in/syeda-nahida-akter-989770114/)