Update README.md

README.md

@@ -8,4 +8,10 @@ datasets:
 
 # Model Card for Mistral-Interact
 
+Mistral-Interact is a powerful and robust variant or Mistral, capable of judging the vagueness of user instruction, actively querying for missing details with suggestions, and explicitly summarizing the detailed and clear user intentions. It has the following features:
+- **Better understanding of user judgments:** Among all the open-source models, Mistral-Interact is the best at predicting task vagueness and missing details that users regard as necessary.
+- **Comprehensive summarization of user intentions:** Mistral-Interact is effective in making an explicit and comprehensive summary based on detailed user intentions.
+- **Enhanced model-user interaction experience:** Mistral-Interact inquires about missing details in vague tasks more reasonably and friendly than other open-source models, thus promoting a clearer understanding of the user’s implicit intentions.
+- **Comparable performance with closed-source GPT-4:** We prove that smaller-scale model experts can approach or even exceed general-purpose large-scale models across various aspects including vagueness judgment, comprehensiveness of summaries, and friendliness of interaction.
+
 We utilize the [model-center](https://github.com/OpenBMB/ModelCenter) framework to conduct full-parameter fine-tuning of [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) using [Intention-in-Interaction(IN3)](https://huggingface.co/datasets/hbx/IN3) dataset on two 80GB A800s. For full details and the usage of this model please read our [paper](https://arxiv.org/abs/2402.09205) and [repo](https://github.com/HBX-hbx/Mistral-Interact).