sandkoan

sandkoan's Stars

• QwenLM/Qwen2.5-Coder

  Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

  Language:Python4.6k366

• HazyResearch/aisys-building-blocks

  Building blocks for foundation models.

  46021

• browser-use/browser-use

  Make websites accessible for AI agents

  Language:Python41.2k4.2k

• rbbydotdev/someday

  Free to host calendar availability picker - open-source cal.com / calendly alternative built on Google-Apps-Script for Gmail users. Built with modern technologies like React, TypeScript, Shadcn/UI, and Vite. https://someday-demo.vercel.app

  Language:TypeScript95439

• cooperleong00/Awesome-LLM-Interpretability

  A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..

  2068

• k3nnethfrancis/client-researcher

  AI agent workflow for generating profiles of clients and running research tasks for them. There is an agent for each part of the process: profile generation, web search, and report writing.

  Language:Python779

• ServiceNow/TapeAgents

  TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle

  Language:Python22921

• FlagOpen/FlagEmbedding

  Retrieval and Retrieval-augmented LLMs

  Language:Python8.9k645

• ictnlp/LLaMA-Omni

  LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

  Language:Python2.8k195

• microsoft/sammo

  A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective Metaprompt Optimization)

  Language:Python64734

• sentient-engineering/agent-q

  agent q - oss advanced reasoning and learning for autonomous ai agents

  Language:Python40185

• sentient-engineering/sentient

  the framework/ sdk that lets you build browser controlling agents in 3 lines of code. join chat @ https://discord.gg/umgnyQU2K8

  Language:Python52160

• OpenBMB/RepoAgent

  An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.

  Language:Python55891

• feizc/FluxMusic

  Text-to-Music Generation with Rectified Flow Transformers

  Language:Python1.7k134

• open-thought/system-2-research

  System 2 Reasoning Link Collection

  80467

• NeoVertex1/SuperPrompt

  SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

  5.9k551

• dlsyscourse/public_notebooks

  Language:Jupyter Notebook5819

• Wilfred/difftastic

  a structural diff that understands syntax 🟥🟩

  Language:Rust21.9k358

• hsfzxjy/handwriter.ttf

  Handwriting synthesis with Harfbuzz WASM.

  Language:Rust45912

• pbelcak/UltraFastBERT

  The repository for the code of the UltraFastBERT paper

  Language:Python51730

• openvla/openvla

  OpenVLA: An open-source vision-language-action model for robotic manipulation.

  Language:Python2.2k280

• H-Freax/Awesome-Video-Robotic-Papers

  This repository compiles a list of papers related to the application of video technology in the field of robotics! Star⭐ the repo and follow me if you like what you see🤩.

  1506

• Zyphra/tree_attention

  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters

  Language:Python1235

• udlbook/udlbook

  Understanding Deep Learning - Simon J.D. Prince

  Language:Jupyter Notebook7.2k1.5k

• luban-agi/Awesome-LLM-reasoning

  A curated paper list on LLM reasoning.

  845

• atfortes/Awesome-LLM-Reasoning

  Reasoning in LLMs: Papers and Resources, including Chain-of-Thought, OpenAI o1, and DeepSeek-R1 🍓

  2.7k157

• sockcymbal/enhanced-llm-reasoning-tree-of-thoughts

  Collection of Tree of Thoughts prompting techniques I've found useful to start with, then stylize, then iterate

  Language:Jupyter Notebook8417

• hacksider/Deep-Live-Cam

  real time face swap and one-click video deepfake with only a single image

  Language:Python44.6k6.6k

• hansbuehler/deephedging

  Implementation of the vanilla Deep Hedging engine

  Language:Jupyter Notebook25451

• mlfoundations/MINT-1T

  MINT-1T: A one trillion token multimodal interleaved dataset.

  80120