Update README.md

README.md

@@ -14,16 +14,9 @@ licence: license
 This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
-## Quick start
+## Task
 
-```python
-from transformers import pipeline
-
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="nnpy/qwen2-7b-instruct-trl-sft-ChartQA", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+This model is fine-tuned for extracting tables from images with better accuracy. This model will extract tables as html table content, so it is easy to convert into any kinda table format such as csv, excel, etc
 
 ## Training procedure