v0.1.7: add selfcheck llm-prompt with OpenAI API

• Add SelfCheckGPT LLM-Prompt with OpenAI API in addition to using open-source model that has already been supported

v0.1.6: add selfcheck llm-prompt method

Add SelfCheckGPT with LLM prompting using an open-source model (e.g., Mistral, Llama)

v0.1.4: more selfcheck method

• Add SelfCheck-NLI (based on DeBERTa-v3 fine-tuned to Multi-NLI), which shows good results
• Add rescale_with_baseline (default=True) to SelfCheck-BERTScore

v0.1.3: add SelfCheck-Ngram

• add SelfCheck-Ngram module into the selfcheckgpt package

v0.1.2: refactor and add MQAG features

Refactor and Add MQAG features

• refactor code into SelfCheck (both SelfCheckMQAG and SelfCheckBERTScore) and MQAG
• add MQAG as many functions of MQAG are used by SelfCheckMQAG
• fix max_length of T5 model (there is no length limit)
• add version.py

v0.1.1: Initial pypi release

Currently, SelfCheckGPT includes the two variants: (1) SelfCheckGPT-MQAG and (2) SelfCheckGPT-BERTScore as described in our preprint on arxiv (dated 15 March 2023)