#
Starred repositories
Bitcoin Mempool AI Assistant is an advanced chatbot designed to provide real-time insights and information about Bitcoin transactions, blockchain data, and market trends
yt-chat is a tool designed to help you summarize any Youtube video.
powerful ai-copilot for quant traders and researchers
A chainlit app that you can use to chat with your SQL database
AIO Data Analyst is an all-in-one intelligent companion for analyzing your data. Easily analyze data, generate insights, and create visualizations with the power of AI.
Bootstrap your large scale forecasting solution on Databricks with Many Models Forecasting (MMF) Project.
Understanding Different Design Choices in Training Large Time Series Models
VisCARS: Graph-Based Context-Aware Visualization Recommendation System
Foundation Models for Time Series
MOMENT: A Family of Open Time-series Foundation Models
Official implementation of "UniTS: A Universal Time Series Analysis Framework Powered by Self-supervised Representation Learning"
A Standard and Fair Time Series Forecasting Benchmark and Toolkit.
✏️0成本LLM微调上手项目，⚡️一步一步使用colab训练法律LLM，基于microsoft/phi-1_5、chatglm3，包含lora微调，全参微调
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
🎯 Task-oriented embedding tuning for BERT, CLIP, etc.
Simple UI for LLM Model Finetuning
Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
TDengine is an open source, high-performance, cloud native time-series database optimized for Internet of Things (IoT), Connected Cars, Industrial IoT and DevOps.
Official code, datasets and checkpoints for "Timer: Generative Pre-trained Transformers Are Large Time Series Models" (ICML 2024)
Gemma 2B with 10M context length using Infini-attention.
Bisheng is an open LLM devops platform for next generation AI applications.
Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods (PVLDB 2024) https://www.vldb.org/pvldb/vol17/p2363-hu.pdf
An awesome & curated list of best LLMOps tools for developers