MarkItDown is a lightweight Python utility for converting various files to Markdown for use with LLMs and related text analysis pipelines. To this end, it is most comparable to textract, but with a focus on preserving important document structure and content as Markdown (includin. Use it to build a structured path from fundamentals to hands-on practice.
Tool for generating high-quality synthetic datasets to fine-tune LLMs. Use it to navigate the topic and choose relevant methods, papers or tools.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. Under real workloads, Mooncake’s innovative architecture enables Kimi to handle 75% more requests while adhering to SLOs. Use it to ground design choices in named patterns, trade-offs and examples.
LLMTools is a user-friendly library for running and finetuning LLMs in low-resource settings. Features include: 🔨 LLM finetuning in 2-bit, 3-bit, 4-bit precision using the ModuLoRA algorithm 🐍 Easy-to-use Python API for quantization, inference, and finetuning 🤖 Modular supp. Use it to navigate the topic and choose relevant methods, papers or tools.
TRL is a cutting-edge library designed for post-training foundation models using advanced techniques like Supervised Fine-Tuning (SFT), Group Relative Policy Optimization (GRPO), and Direct Preference Optimization (DPO). Built on top of the 🤗 Transformers ecosystem, TRL supports. Use it to navigate the topic and choose relevant methods, papers or tools.
StageRAG is a lightweight, production-ready RAG framework designed to give you precise control over the speed-versus-accuracy trade-off. It allows you to build high-factuality applications while gracefully managing uncertainty in LLM responses. Use it to navigate the topic and choose relevant methods, papers or tools.
Simple Python bindings for @ggerganov's llama.cpp library. This package provides:. Use it to ground design choices in named patterns, trade-offs and examples.
Official PyTorch implementation for Extreme Compression of Large Language Models via Additive Quantization. Use it to navigate the topic and choose relevant methods, papers or tools.
Quick Start • Architecture • Training • Validation • Inference • Examples • Configuration • Troubleshooting. Use it to ground design choices in named patterns, trade-offs and examples.
A community-driven hub of 42+ runnable notebooks covering RAG techniques from foundational to cutting-edge - the intuition, the code, and the references to build more accurate, context-rich retrieval systems. Use it as a repeatable review, validation or hardening pass.
This repo collects papers, documents, and codes about model quantization for anyone who wants to research it. We are continuously improving the project. Use it to navigate the topic and choose relevant methods, papers or tools.
MedAlpaca expands upon both Stanford Alpaca and AlpacaLoRA to offer an advanced suite of large language models specifically fine-tuned for medical question-answering and dialogue applications. Our primary objective is to deliver an array of open-source language models, paving the way for seamless development of medical chatbot solutions.
A web interface for Stable Diffusion, implemented using Gradio library. Detailed feature showcase with images: Make sure the required dependencies are met and follow the instructions available for: Alternatively, use online services (like Google Colab): 1.
Implementation of Band Split Roformer , SOTA Attention network for music source separation out of ByteDance AI Labs. They beat the previous first place by a large margin.
Implementation of SoundStorm , Efficient Parallel Audio Generation from Google Deepmind, in Pytorch. They basically applied MaskGiT to the residual vector quantized codes from Soundstream .
Kindle | Paperback | PDF [Leanpub] | PDF [Gumroad] You can easily load the notebooks directly from GitHub using Colab and run them using a GPU provided by Google. You need to be logged in a Google Account of your own.
SimpleTuner is geared towards simplicity, with a focus on making the code easily understood. This codebase serves as a shared academic exercise, and contributions are welcome.
Free, open-source Beamer slide decks and code for Machine Learning, Deep Learning, NLP, Generative AI, Maths for ML, and Python, from 1-hour seminars to full courses. Everything here, including slides, code, and notes, has been built by learning from, and citing, the best public material available, and is given back under an open license so anyone can teach, learn, or build on it.
Get structured, fully typed, and validated JSON outputs from OpenAI and Anthropic models. Under the hood, zod-gpt uses functions to coerce the model to always respond as function calls.
A powerful local RAG (Retrieval Augmented Generation) application that lets you chat with your PDF documents using Ollama and LangChain. This project includes multiple interfaces: a modern Next.js web app, a Streamlit interface, and Jupyter notebooks for experimentation.
MarkItDown is a lightweight Python utility for converting various files to Markdown for use with LLMs and related text analysis pipelines. To this end, it is most comparable to textract, but with a focus on preserving important document structure and content as Markdown (includin. Use it to build a structured path from fundamentals to hands-on practice.
Tool for generating high-quality synthetic datasets to fine-tune LLMs. Use it to navigate the topic and choose relevant methods, papers or tools.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. Under real workloads, Mooncake’s innovative architecture enables Kimi to handle 75% more requests while adhering to SLOs. Use it to ground design choices in named patterns, trade-offs and examples.
LLMTools is a user-friendly library for running and finetuning LLMs in low-resource settings. Features include: 🔨 LLM finetuning in 2-bit, 3-bit, 4-bit precision using the ModuLoRA algorithm 🐍 Easy-to-use Python API for quantization, inference, and finetuning 🤖 Modular supp. Use it to navigate the topic and choose relevant methods, papers or tools.
TRL is a cutting-edge library designed for post-training foundation models using advanced techniques like Supervised Fine-Tuning (SFT), Group Relative Policy Optimization (GRPO), and Direct Preference Optimization (DPO). Built on top of the 🤗 Transformers ecosystem, TRL supports. Use it to navigate the topic and choose relevant methods, papers or tools.
StageRAG is a lightweight, production-ready RAG framework designed to give you precise control over the speed-versus-accuracy trade-off. It allows you to build high-factuality applications while gracefully managing uncertainty in LLM responses. Use it to navigate the topic and choose relevant methods, papers or tools.
Simple Python bindings for @ggerganov's llama.cpp library. This package provides:. Use it to ground design choices in named patterns, trade-offs and examples.
Official PyTorch implementation for Extreme Compression of Large Language Models via Additive Quantization. Use it to navigate the topic and choose relevant methods, papers or tools.
Quick Start • Architecture • Training • Validation • Inference • Examples • Configuration • Troubleshooting. Use it to ground design choices in named patterns, trade-offs and examples.
A community-driven hub of 42+ runnable notebooks covering RAG techniques from foundational to cutting-edge - the intuition, the code, and the references to build more accurate, context-rich retrieval systems. Use it as a repeatable review, validation or hardening pass.
This repo collects papers, documents, and codes about model quantization for anyone who wants to research it. We are continuously improving the project. Use it to navigate the topic and choose relevant methods, papers or tools.
MedAlpaca expands upon both Stanford Alpaca and AlpacaLoRA to offer an advanced suite of large language models specifically fine-tuned for medical question-answering and dialogue applications. Our primary objective is to deliver an array of open-source language models, paving the way for seamless development of medical chatbot solutions.
A web interface for Stable Diffusion, implemented using Gradio library. Detailed feature showcase with images: Make sure the required dependencies are met and follow the instructions available for: Alternatively, use online services (like Google Colab): 1.
Implementation of Band Split Roformer , SOTA Attention network for music source separation out of ByteDance AI Labs. They beat the previous first place by a large margin.
Implementation of SoundStorm , Efficient Parallel Audio Generation from Google Deepmind, in Pytorch. They basically applied MaskGiT to the residual vector quantized codes from Soundstream .
Kindle | Paperback | PDF [Leanpub] | PDF [Gumroad] You can easily load the notebooks directly from GitHub using Colab and run them using a GPU provided by Google. You need to be logged in a Google Account of your own.
SimpleTuner is geared towards simplicity, with a focus on making the code easily understood. This codebase serves as a shared academic exercise, and contributions are welcome.
Free, open-source Beamer slide decks and code for Machine Learning, Deep Learning, NLP, Generative AI, Maths for ML, and Python, from 1-hour seminars to full courses. Everything here, including slides, code, and notes, has been built by learning from, and citing, the best public material available, and is given back under an open license so anyone can teach, learn, or build on it.
Get structured, fully typed, and validated JSON outputs from OpenAI and Anthropic models. Under the hood, zod-gpt uses functions to coerce the model to always respond as function calls.
A powerful local RAG (Retrieval Augmented Generation) application that lets you chat with your PDF documents using Ollama and LangChain. This project includes multiple interfaces: a modern Next.js web app, a Streamlit interface, and Jupyter notebooks for experimentation.