Stars
🎓 无需编写任何代码即可轻松创建漂亮的学术网站 Easily create a beautiful academic résumé or educational website using Hugo and GitHub. No code.
llama3 implementation one matrix multiplication at a time
[MM'24 Oral] Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
An Open-Source Package for Knowledge Embedding (KE)
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.
List of Molecular and Material design using Generative AI and Deep Learning
Astrofy is a free and open-source template for your Personal Portfolio Website built with Astro and TailwindCSS. Create in minutes a website with Blog, CV, Project Section, Store and RSS Feed.
Repository for Text2Mol: Cross-Modal Molecular Retrieval with Natural Language Queries
Code and data for "The Power of Noise: Redefining Retrieval for RAG Systems"
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
[ICLR 2022 spotlight]GreaseLM: Graph REASoning Enhanced Language Models for Question Answering
Letta (fka MemGPT) is a framework for creating stateful LLM services.
A Theory and Practical Guide to Deep Learning Semantic Segmentation
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
When FLUE Meets FLANG: Benchmarks and Large Pretrained Language Model for Financial Domain
ChatLaw:A Powerful LLM Tailored for Chinese Legal. 中文法律大模型
[ACL 2024] Official resources of "ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models".
👾 A Python API wrapper for Poe.com. With this, you will have free access to GPT-4, Claude, Llama, Gemini, Mistral and more! 🚀
Awesome LLM compression research papers and tools.
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
Official implementation of our ICRA'22 paper: SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving
Repo ISWC-2023 Tekgen Corpus Submission