Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

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

MCP server for Atlassian tools (Confluence, Jira)

🤗 smolagents: a barebones library for agents that think in code.

[AAAI 2025] VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding

Papers and codes about Quantized Networks for easier survey and reference.

A repository for research on medium sized language models.

Best practice for training LLaMA models in Megatron-LM

Reference implementation for DPO (Direct Preference Optimization)

Tools for managing datasets for governance and training.

Identifying the language of input text using character-level n-grams, with support for 45 languages

LLM training code for Databricks foundation models

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

This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious current problem in widespread adoption of LLM's for many real…

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

A collection of libraries to optimise AI model performances

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

COYO-700M: Large-scale Image-Text Pair Dataset

Ask Me Anything language model prompting

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

A dataset of crowdsourced ratings for machine-generated image captions

Extended COCO Validation (ECCV) Caption dataset (ECCV 2022)

Train Dense Passage Retriever (DPR) with a single GPU

Official DeiT repository

A repository containing datasets and tools to train a watermark classifier.

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Source code and data used in the papers ViQuAE (Lerner et al., SIGIR'22), Multimodal ICT (Lerner et al., ECIR'23) and Cross-modal Retrieval (Lerner et al., ECIR'24)

A concise but complete implementation of CLIP with various experimental improvements from recent papers

Summarizing and Exploring Tabular Data in Conversational Search (SIGIR '20)