Stars
Fully open reproduction of DeepSeek-R1
A MacOS application showcasing DeepSeek's R1 Distill Qwen 1.5B LLM running locally with MLX Model Manager
Chat with any codebase in under two minutes | Fully local or via third-party APIs
A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Official code for VisProg (CVPR 2023 Best Paper!)
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
Source code for Twitter's Recommendation Algorithm
This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Source code for 'A Multi-Strategy based Pre-Training Method for Cold-Start Recommendation'
PyTorch code for Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles (DANCE)
A playbook for systematically maximizing the performance of deep learning models.
General technology for enabling AI capabilities w/ LLMs and MLLMs
MLNLP: This repository is a collection of AI top conferences papers (e.g. ACL, EMNLP, NAACL, COLING, AAAI, IJCAI, ICLR, NeurIPS, and ICML) with open resource code
Train transformer language models with reinforcement learning.
A modular RL library to fine-tune language models to human preferences
fast-stable-diffusion + DreamBooth
Language model alignment-focused deep learning curriculum
Repository for DEMETR: Diagnosing Evaluation Metrics for Translation