Block or Report
Block or report ash0ts
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
AutoEvals is a tool for quickly and easily evaluating AI model outputs using best practices.
A compute framework for building Search, RAG, Recommendations and Analytics over complex (structured+unstructured) data, with ultra-modal vector embeddings.
A lightweight framework for building LLM-based agents
A community-maintained Python framework for creating mathematical animations.
Open-source observability for your LLM application, based on OpenTelemetry
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
Create agents that monitor and act on your behalf. Your agents are standing by!
Example repository for running Snowflake Arctic on Streamlit
music21 is a Toolkit for Computational Musicology
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
Official repo for WavCraft, an AI agent for audio creation and editing
GPT based autonomous agent that does online comprehensive research on any given topic
The only reliable agent framework built on top of the latest OpenAI Assistants API.
Convert PDF to markdown quickly with high accuracy
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"
aider is AI pair programming in your terminal
[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Open-Sora: Democratizing Efficient Video Production for All
Interact with your documents using the power of GPT, 100% privately, no data leaks
Resources for the FC 2024 LLM workshop
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.