Stars
Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
A vector search SQLite extension that runs anywhere!
An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"
Training Sparse Autoencoders on Language Models
RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a …
Python toolkit for corpus analysis: tokenization, lexical diversity, vocabulary growth prediction, entropy measures, and Zipf/Heaps visualizations.
Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors
utilities for loading and running text embeddings with onnx
Fast and consistently responsive apps using a single function call
making GPT2 transformer weights by hand
Distribute and run LLMs with a single file.
Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)
Tools for working with the Abstraction & Reasoning Corpus
DSPy: The framework for programming—not prompting—foundation models
A library for mechanistic interpretability of GPT-style language models
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Finetuning large language models for GDScript generation.
Flask app for article abstract and listing pages