Update README.md

README.md

@@ -3,10 +3,11 @@ license: gpl-3.0
 language:
 - en
 ---
-# TL;DR
-**ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning**
+
+# ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
 
 Venue: **ACL 2024 (Findings)**
+
 Paper Link: https://arxiv.org/abs/2403.09028 
 
 The abstract of the paper states that: 
@@ -14,12 +15,12 @@ The abstract of the paper states that:
 # Web Demo
 If you wish to quickly try our model, you can access our public web demo hosted on the Hugging Face Spaces platform with a friendly interface!
 
-[ChartInstruct-Llama2 Web Demo](https://huggingface.co/spaces/ahmed-masry/UniChart-Base) |
+[ChartInstruct-Llama2 Web Demo](https://huggingface.co/spaces/ahmed-masry/UniChart-Base)
 
 # Inference
 You can easily use our models for inference with the huggingface library! 
 You just need to do the following:
-1. Chage the _imag_path_ to your chart example image path on your system
+1. Chage the _image_path_ to your chart example image path on your system
 2. Write the _input_text_.
 
 ```
@@ -32,8 +33,8 @@ torch.hub.download_url_to_file('https://raw.githubusercontent.com/vis-nlp/ChartQ
 
 image_path = "/content/chart_example_1.png"
 input_text = "Question: What is the share of respondants who prefer Whatsapp in the 18-29 age group?"
-input_prompt = f"<image>\n Question: {input_text} Answer: "
 
+input_prompt = f"<image>\n Question: {input_text} Answer: "
 
 model = LlavaForConditionalGeneration.from_pretrained("ahmed-masry/ChartInstruct-LLama2", torch_dtype=torch.float16)
 processor = AutoProcessor.from_pretrained("ahmed-masry/ChartInstruct-LLama2")