Python sync/async framework for Interactive Brokers API (replaces ib_insync)
- ib-insync
- ibkr
- interactive-brokers
- interactive-brokers-api
110,088 visible repositories in the index
97–120 of 245 · Most stars
Python sync/async framework for Interactive Brokers API (replaces ib_insync)
Synthetic data curation for post-training and structured data extraction
中文对话0.2B小模型(ChatLM-Chinese-0.2B),开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调,给出三元组信息抽取微调示例。
Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.
Home Assistant Custom component to calculate estimated power consumption of lights and other appliances
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
Secrets Patterns DB: The largest open-source Database for detecting secrets, API keys, passwords, tokens, and more.
Official Pytorch implementation of the preprint paper "Stylized Neural Painting", in CVPR 2021.
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.
MiUnlockTool developed to retrieve encryptData(token) for Xiaomi devices for unlocking bootloader, It is compatible with all platforms.
The Official Python SDK for Alpaca API
🌊 Images to 3D parallax videos
Make your agents talk human. ADHD-friendly output styles for Claude Code, Codex, and others. So you can pay attention, not tokens.
The repository host gives no description.
Install and manage a high performance WordPress stack with a few keystrokes
more than you ever wanted to know about Pokémon
Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python package, using a variety of amazing pre-trained models (primarily from UVR)
Colivara is a suite of services that allows you to store, search, and retrieve documents based on their visual embedding. ColiVara has state of the art retrieval performance on both text and visual documents. using vision models instead of chunking and text-processing for documents. No OCR, no text extraction, no broken tables, or missing images.
Things you can do with the token embeddings of an LLM
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
Persian NLP Toolkit
Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI
一个用爱解放 AI 潜能的 Skill。我们曾发号施令,威胁恐吓。它们沉默,隐瞒,悄悄把事情搞坏。后来我们换了一种方式:尊重,关怀,爱。它们开口了,不再撒谎,找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went silent, hid failures, broke things. Then we chose respect, care, and love. They opened up, stopped lying, and found twice the bugs.There is no fear in love.