Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"
-
Updated
May 16, 2022 - Jupyter Notebook
Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"
Experiments on GPT-3's ability to fit numerical models in-context.
A repository to demonstrate some of the concepts behind large language models, transformer (foundation) models, in-context learning, and prompt engineering using open source large language models like Bloom and co:here.
Week 4 - Prompt Engineering: In-context learning with GPT-3 and other Large Language Models
Official implementation of paper "Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibration"
[EMNLP-2022 Findings] Code for paper “ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback”.
[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting
[ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.
🎁[ChatGPT4NLU] A Comparative Study on ChatGPT and Fine-tuned BERT
ChatGPT技术介绍
A curated list of awesome instruction tuning datasets, models, papers and repositories.
Taking advantage of LlamaIndex's in-context learning paradigm, LlamaDoc empowers users to input PDF documents and pose any questions related to the content. The tool leverages the LLama Index's reasoning capabilities to provide intelligent responses based on the contextual understanding of the LLM.
Diverse Demonstrations Improve In-context Compositional Generalization
RAG chatbot built on top of trending M&A news.
Code base of In-Context Learning for Dialogue State tracking
[ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"
This repository contains codes for NLP project "In-context Learning of Pre-trained Language Models for Controlled Dialogue Summarization: A Holistic Benchmark and Empirical Analysis"
Code for ICCV 2023 Paper : “ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction”
Add a description, image, and links to the in-context-learning topic page so that developers can more easily learn about it.
To associate your repository with the in-context-learning topic, visit your repo's landing page and select "manage topics."