---
license: mit
language:
- en
pipeline_tag: text-generation
base_model:
- mistralai/Mistral-7B-Instruct-v0.2
---

# Uncertain-Mistral-7B

We use the original [Mistral-7B-Instruct-v0.2](https://huggingface.co/meta-llama/Llama-2-7b-hf) by finetuning it on selected samples from our data(https://github.com/RUCAIBox/HaluEval). 
We then use it in our LoGU task to target at the uncertainty-suppression and uncertain-misalignment problem.
More details are provided in our [Github](https://github.com/hillzhang1999/ICD) and [Paper]().