Scientific multimodal instruction tuning with large language and vision models.

Synthetic data curation for post-training and structured data extraction

React + Next.js template for research websites (for PhD students, researchers, etc)

Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

Data processing with ML, LLM and Vision LLM

A large-scale information-rich web dataset, featuring millions of real clicked query-document labels

potato: portable text annotation tool

This is a repo with links to everything you'd ever want to learn about data engineering

AICI: Prompts as (Wasm) Programs

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

AgentSearch is a framework for powering search agents and enabling customizable local search.

library supporting NLP and CV research on scientific papers

Implementation of Nougat Neural Optical Understanding for Academic Documents

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

AI Observability & Evaluation

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

✨✨Latest Advances on Multimodal Large Language Models

A curation of awesome tools, documents and projects about LLM Security.

Code/Data for the paper: "LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding"

Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).

the LLM vulnerability scanner

LLM Prompt Injection Detector

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

Multi-tool for semantic search