Stars
Scalable RL solution for advanced reasoning of language models
Code for ICLR 2024 paper "CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets"
A large-scale, fine-grained, diverse preference dataset (and models).
Official Repo for ICLR 2024 paper MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback by Xingyao Wang*, Zihan Wang*, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng and …
[NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations".
Source code for ACL 2023 Findings paper "From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework"
Code for ACL 2023 paper "A Close Look into the Calibration of Pre-trained Language Models"
Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
A Parallel Completion Python Library that boosts your OpenAI-API query with task queue & multiprocessing.
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
An (unofficial) implementation of Focal Loss, as described in the RetinaNet paper, generalized to the multi-class case.
An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.