Starred repositories
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
A framework for few-shot evaluation of language models.
Automatic Evals for Instruction-Tuned Models
LLM training code for Databricks foundation models
A Data Streaming Library for Efficient Neural Network Training
LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/l…
🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
A simple repo for viewing attention maps of llama 3.1
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Machine Learning Engineering Open Book
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
On-device Speech Recognition for Apple Silicon
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
A series of large language models trained from scratch by developers @01-ai
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…
Configuration with Dataclasses+YAML+Argparse. Fork of Pyrallis
Training and serving large-scale neural networks with auto parallelization.
Named Tensors for Legible Deep Learning in JAX
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image …
An LLM playground you can run on your laptop
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
Simple Image Search powered by Multimodal Foundation Models (OpenAI Clip and Microsoft GLIP)