Open-Sora: Democratizing Efficient Video Production for All

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Convert PDF to markdown quickly with high accuracy

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

Go ahead and axolotl questions

Data files of German Decompounder for Apache Lucene / Apache Solr / Elasticsearch

Agents Capable of Self-Editing Their Prompts / Python Code

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

All things prompt engineering

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

Python bindings for llama.cpp

A high-throughput and memory-efficient inference and serving engine for LLMs

Inference code for Mistral and Mixtral hacked up into original Llama implementation

Fine-tune mistral-7B on 3090s, a100s, h100s

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

A Kurtosis package for Python data engineers, deploying a Jupyter notebook along with a configurable set of databases, and a visualization tool (Streamlit)

Collection of Datasets for Legal Text Processing

large language model for mastering data analysis using pandas

Open-source observability for your LLM application, based on OpenTelemetry

Reference implementation for DPO (Direct Preference Optimization)

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Zep: Long-Term Memory for ‍AI Assistants.

Awesome papers about unifying LLMs and KGs

Run any open-source LLMs, such as Llama 3.1, Gemma, as OpenAI compatible API endpoint in the cloud.

Force-directed graph rendered on HTML5 canvas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

Large Language Model Text Generation Inference

Tune any FALCON in 4-bit