Pinned Repositories
baby-llm
RedisXANN
redis x ANN vss
RedisXLM
redis x language model inference (load trained model); size (tiny|t, small|s, medium|m, large|l) with quantization; NOTE: redis embedded language model, available for stand-alone version only
RedisXSlot
redis x slot module, async block migrate/restore, don't block or less block other cmd.
craftsman
a craftsman, try best to give a best practicable solution for biz~
doraemon-nb
ipython notebooks do some sample experiments , make some idea
geo
php 扩展(地图相关的操作)
iowrapper
io_uring lib or syscall wrapper; add some benchmark for io_uring experimental study
perf-book-cn
https://github.com/dendibakh/perf-book gitbook在线电子书，翻译成中文原始markdown文档
weedge's Repositories
weedge/doraemon-nb
ipython notebooks do some sample experiments , make some idea
weedge/Agora-Python-Server-SDK
weedge/agora-realtime-ai-api
fork to support video track, support low version python
weedge/apipeai
Multimodal Content pipe to Multimodal Content with AI , a big idea
weedge/docling
Get your documents ready for gen AI
weedge/Freeze-Omni
✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM；关注在如何freeze LLM, 推理延迟比较高，应该可以通过工程手段优化，因为语音模型是分开的
weedge/GLM-4-Voice
GLM-4-Voice | 端到端中英语音对话模型； 虽然技术报告还未出，实操延迟和freeze-omni 一样高，和单独使用ASR，llm, TTS没多大差别，仅仅是让GLM-4增加了理解audio的能力，中间产物，延时和模型准确率的折中
weedge/GOT-OCR2.0
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
weedge/hertz-dev
first base model for full-duplex conversational audio
weedge/higress
🤖 AI Gateway | AI Native API Gateway
weedge/HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model Training
weedge/ichigo
Llama3.1 learns to Listen ; 复现训练过程！
weedge/mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
weedge/mini-omni2
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
weedge/ML-DL-note
keyword and algorithm about ML, DL on text, audio, vision case
weedge/moshi
weedge/n8n
Free and source-available fair-code licensed workflow automation tool. Easily automate tasks across different services.
weedge/nexa-sdk
Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), auto-speech-recognition (ASR), and text-to-speech (TTS) capabilities.
weedge/open-interpreter
A natural language interface for computers
weedge/pdf-extract-api
Document (PDF) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown; for apipeai to learn from this repos
weedge/pipecat
Open Source framework for voice and multimodal conversational AI
weedge/podcastfy
Transforming Multi-Sourced Text into Captivating Multi-Lingual Audio Conversations with GenAI
weedge/prime
prime is a framework for efficient, globally distributed training of AI models over the internet.
weedge/RT-DETR
[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥
weedge/sapiens
High-resolution models for human tasks.
weedge/swarm
Framework for building, orchestrating and deploying multi-agent systems. Managed by OpenAI Solutions team. Experimental framework.
weedge/TEN-Agent
TEN Agent is a world-class multimodal AI agent integrated with the OpenAI Realtime API, RTC, and features weather checks, web search, vision, and RAG. 主要是了解框架，结合.json的两个流程配置文件，以及调度不同的节点，节点使用不同开发语言开发；至于前端UI和golang写的流程配置任务节点启动管理服务可以借鉴一下，思路一样；主要是底层框架; chromium is all u attention
weedge/ten_framework
TEN, the Next-Gen AI-Agent Framework, the world's first truly real-time multimodal AI agent framework.
weedge/vision_transformer
ViT
weedge/VITA
✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM。主要是了解下训练过程。