#
Lists (2)
Starred repositories
website untuk mencari pasar malam terdekat anda
We want to compare how good Qwen3-1.7B-Base using B200 to continue pretraining on Malaysian multi-lingual corpus on different mixed precision training with proper truncated multi-packing.
"AI-Trader: Can AI Beat the Market?" Live Trading: https://hkuds.github.io/AI-Trader/
Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
Comprehensive LLM testing suite for safety, performance, bias, and compliance, equipped with methodologies and tools to enhance the reliability and ethical integrity of models like OpenAI's GPT ser…
18
Updated Apr 15, 2024
[ICCV'25 oral] Official Code for "LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models"
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's …
Transform your 3D texturing workflow with the power of generative AI, directly within Blender!
🎒 Token-Oriented Object Notation (TOON) – JSON for LLM prompts at half the tokens. Official spec & TypeScript implementation.
Real-time KL traffic viewer for ASEAN Summit with interactive maps, color-coded roads, and geolocation support
Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.
Pen and paper exercises in machine learning
Face Depixelizer based on "PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models" repository.
Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)
CUDA accelerated rasterization of gaussian splatting
Fast and Universal 3D reconstruction model for versatile tasks
Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model
An open-source, 3D-printed parallel gripper for precise control in robotics arms, compatible with Feetech STS3215 and Waveshare ST3215 servos.
Event-based Vision Resources. Community effort to collect knowledge on event-based vision technology (papers, workshops, datasets, code, videos, etc)
Un-LOCC: Universal Lossy Optical Context Compression for Vision-Based Language Models Achieve nearly 3x token compression at over 93% retrieval accuracy using existing Vision-Language Models.
Salesforce Enterprise Deep Research
🧠 世界上覆盖最全的优秀Qwen提示语大全，欢迎贡献你的提示词。🧠 The most comprehensive collection of excellent Qwen prompts in the world. Feel free to contribute your own prompts!
This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.