Publish versioned Markdown. Build focused streams. Give people and agents only the context they need.
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.
⚠️ Warning: Not Actively Maintained This repository is no longer actively maintained. For a more up-to-date alternative, please visit the LitGPT project: https://github.com/Lightning-AI/litgpt , which serves as the successor to this repository.
A Rust, Python and gRPC server for text generation inference. Used in production at Hugging Face to power Hugging Chat, the Inference API and Inference Endpoints.
This is a port of BlinkDL/RWKV-LM to ggerganov/ggml. Besides the usual FP32, it supports FP16, quantized INT4, INT5 and INT8 inference.
KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models, inspired by the original KoboldAI. It's a single self-contained distributable that builds off llama.cpp and adds many additional powerful features.
We also introduce a diffusion-based value model that reduces variance and improves stability during optimization. Based on TraceRL, we derive a series of diffusion language models, TraDo, which achieve state-of-the-art performance on math and coding reasoning tasks.
I've started to work on reimplementation of the library here: FastTensors Please star it if you'd like to see GGML-compatible implementation in pure Go. Please check out my related project Booster We dream of a world where fellow ML hackers are grokking REALLY BIG GPT models in their homelabs without having GPU clusters consuming a shit tons of $$$.
This repo supports the paper "QLoRA: Efficient Finetuning of Quantized LLMs", an effort to democratize access to LLM research. QLoRA uses bitsandbytes for quantization and is integrated with Hugging Face's PEFT and transformers libraries.
A self-evolving librarian agent for document collections. AutoRAG searches your PDFs, wikis, notes, research papers, and knowledge bases — then curates the results into clean, numbered knowledge units.
⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡ [[Tech Report]](assets/llmzoo.pdf) technology gifted by the creator. For example, many pioneers have made great efforts to spread the use of light bulbs and vaccines to developing countries.
Publish versioned Markdown. Build focused streams. Give people and agents only the context they need.
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.
⚠️ Warning: Not Actively Maintained This repository is no longer actively maintained. For a more up-to-date alternative, please visit the LitGPT project: https://github.com/Lightning-AI/litgpt , which serves as the successor to this repository.
A Rust, Python and gRPC server for text generation inference. Used in production at Hugging Face to power Hugging Chat, the Inference API and Inference Endpoints.
This is a port of BlinkDL/RWKV-LM to ggerganov/ggml. Besides the usual FP32, it supports FP16, quantized INT4, INT5 and INT8 inference.
KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models, inspired by the original KoboldAI. It's a single self-contained distributable that builds off llama.cpp and adds many additional powerful features.
We also introduce a diffusion-based value model that reduces variance and improves stability during optimization. Based on TraceRL, we derive a series of diffusion language models, TraDo, which achieve state-of-the-art performance on math and coding reasoning tasks.
I've started to work on reimplementation of the library here: FastTensors Please star it if you'd like to see GGML-compatible implementation in pure Go. Please check out my related project Booster We dream of a world where fellow ML hackers are grokking REALLY BIG GPT models in their homelabs without having GPU clusters consuming a shit tons of $$$.
This repo supports the paper "QLoRA: Efficient Finetuning of Quantized LLMs", an effort to democratize access to LLM research. QLoRA uses bitsandbytes for quantization and is integrated with Hugging Face's PEFT and transformers libraries.
A self-evolving librarian agent for document collections. AutoRAG searches your PDFs, wikis, notes, research papers, and knowledge bases — then curates the results into clean, numbered knowledge units.
⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡ [[Tech Report]](assets/llmzoo.pdf) technology gifted by the creator. For example, many pioneers have made great efforts to spread the use of light bulbs and vaccines to developing countries.