lingjiekong
Follow
Lists (20)
Starred repositories
Cross-platform, fast, feature-rich, GPU based terminal
This repository contains the Hugging Face Agents Course.
Learn AI/ML and prepare for interviews using free resources.
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Democratizing Reinforcement Learning for LLMs
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…
📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
📖A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, Flash-Attention, Paged-Attention, Parallelism, etc. 🎉🎉
A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.
Prefect is a workflow orchestration framework for building resilient data pipelines in Python.
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
(ECCV 2024) Code for V-IRL: Grounding Virtual Intelligence in Real Life
Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Witness the aha moment of VLM with less than $3.
Everything you need to build state-of-the-art foundation models, end-to-end.
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
A browser automation framework and ecosystem.
Open Thoughts: Fully Open Data Curation for Thinking Models
A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions
Building a comprehensive and handy list of papers for GUI agents
Janus-Series: Unified Multimodal Understanding and Generation Models
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
