Highlights
- Pro
Stars
A guide on how to compile mistral-nemo to a TensorRT-LLM engine and serve it on Triton-Inference-Server
IBeam is an authentication and maintenance tool used for the Interactive Brokers Client Portal Web API Gateway.
Python sync/async framework for Interactive Brokers API (replaces ib_insync)
Python bindings for Notion Database API
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progres…
🍃 JavaScript library for mobile-friendly interactive maps 🇺🇦
A Native-PyTorch Library for LLM Fine-tuning
Represent trained machine learning models as Pyomo optimization formulations
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
HISTDATA - Dataset composed of all FX trading pairs / Crude Oil / Stock Indexes. Simple API to retrieve 1 Minute data (and tick data) Historical FX Prices (up to date).
User-friendly WebUI for LLMs (Formerly Ollama WebUI)
KeyCastr, an open-source keystroke visualizer
Python sync/async framework for Interactive Brokers API
Country polygons as GeoJSON in a datapackage
Julia package to generate, estimate, and forecast long memory processes
A web-based collaborative LaTeX editor
Streamlit Component for rendering Folium maps
LlamaIndex is a data framework for your LLM applications
LLM Chain for answering questions from documents with citations
20 high-performance LLMs with recipes to pretrain, finetune and deploy at scale.