Stars
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
LLM-Powered Semi-Structured Table Question Answering
ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)
Full-featured async (tokio-based) postgres connection pool (like r2d2)
A blazing fast inference solution for text embeddings models
A rust implementation of some popular snowball stemming algorithms
The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
Trace LLM calls (and others) and visualize them in WandB, as interactive SVG or using a streaming local webapp
Notebooks and various random fun
A repository for transformer critique learning and generation
OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.
A library to conduct ranking experiments with transformers.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
DSPy: The framework for programming—not prompting—language models
LlamaIndex is the leading document agent and OCR platform
An Open-Source Package for Information Retrieval
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptatio…
PromptBERT: Improving BERT Sentence Embeddings with Prompts
An Open-Source Framework for Prompt-Learning.
A python library for the Semantic Scholar (S2) API with typed pydantic objects and various nifty functionalities.
A plug-and-play library for parameter-efficient-tuning (Delta Tuning)
Using machine learning on your anki collection to enhance the scheduling via semantic clustering and semantic similarity
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
Expanding natural instructions