An automated tool for discovering insights from research papaer corpora

Benchmarking library for RAG

Collection of links, tutorials and best practices of how to collect the data and build end-to-end RLHF system to finetune Generative AI models

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

Enforce the output format (JSON Schema, Regex etc) of a language model

All of the ad-hoc things you're doing to manage incidents today, done for you, and much more!

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

A template for a FastAPI based Serverless Framework microservice running on AWS Lambda

FastAPI + ODMantic example

GPU Development in Python 101 tutorial

Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

Official code and data for ACL-2024 paper "X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions"

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

A self-organizing file system with llama 3

llama3 implementation one matrix multiplication at a time

Data extraction with Donut ML model

Full stack, modern web application template. Using FastAPI, React, SQLModel, PostgreSQL, Docker, GitHub Actions, automatic HTTPS and more.

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

An ML Systems Onboarding list

Data processing with ML and LLM

LLM training code for Databricks foundation models

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

Pytorch Datasets for Easy-To-Hard

Stable Diffusion with Core ML on Apple Silicon

33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading