Starred repositories
Build and query dynamic, temporally-aware Knowledge Graphs
LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
🥚 Transform PDF to JSON or Markdown with ease and speed 🐣
Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.
An open-source RAG-based tool for chatting with your documents.
Parse SEC EDGAR HTML documents into a tree of elements that correspond to the visual (semantic) structure of the document.
Investment Research for Everyone, Everywhere.
A lightweight framework for building LLM-based agents
A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
Reference implementation for DPO (Direct Preference Optimization)
GPT-4 Equipped with Numeric Calculation
An Open Source Toolkit For LLM Distillation
Data and code for EMNLP 2021 paper "FinQA: A Dataset of Numerical Reasoning over Financial Data"
Dataset for NAACL 2021 paper: "QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization"
[EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627
LLMs in Finance - Generative AI - AI Agents
Agentic components of the Llama Stack APIs
Task-based Agentic Framework using StrictJSON as the core
Arena-Hard-Auto: An automatic LLM benchmark.
Meta + Rayban Glasses whatsapp bot integration
A project that optimizes Whisper for low latency inference using NVIDIA TensorRT
🎙️ Speak with AI - Run locally using ollama or OpenAI - XTTS or OpenAI Speech or ElevenLabs