Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Released model weights, reference implementations and architecture research.
Signals: large-language-models, llm, foundation-models, transformer, gpt, llama, mistral, qwen
1,455 results
Prov-GigaPath: A whole-slide foundation model for digital pathology from real-world data
[ICLR 2024] DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genome
Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena
NeurIPS'24 Workshop - UniTable: Towards a Unified Table Foundation Model
Large Language & Foundation Models for Time Series.
Building blocks for foundation models.
An Open Foundation Model and Benchmark to Accelerate Generative Recommendation
Vision Foundation Models for Medical AI, including RETFound, DINOv2, DINOv3
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
MOMENT: A Family of Open Time-series Foundation Models, ICML'24
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Comprehensive tools and frameworks for developing foundation models tailored to recommendation systems.
Biological foundation modeling from molecular to genome scale
Pathology Foundation Model - Nature Medicine
Painter & SegGPT Series: Vision Foundation Models from BAAI
Foundation model for weather & climate
A curated list of foundation models for vision and language tasks
Open weights language model from Google DeepMind, based on Griffin.
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
A mini, open-weights, version of our Proxy assistant.
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL
This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.
Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).
24,540 repositories in the index in total.
