vgel

vgel's Stars

• karpathy/LLM101n

  LLM101n: Let's build a Storyteller

  30.3k2.4k01.7k

• Mozilla-Ocho/llamafile

  Distribute and run LLMs with a single file.

  Language:C++20.6k1774271k

• stanfordnlp/dspy

  DSPy: The framework for programming—not prompting—language models

  Language:Python19.1k1448321.5k

• Lightning-AI/litgpt

  20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

  Language:Python10.8k947881.1k

• srush/GPU-Puzzles

  Solve puzzles. Learn CUDA.

  Language:Jupyter Notebook10k19232861

• InternLM/InternLM

  Official release of InternLM2.5 base and chat models. 1M context support

  Language:Python6.5k58334460

• asg017/sqlite-vec

  A vector search SQLite extension that runs anywhere!

  Language:C4.2k54114134

• openai/transformer-debugger

  Language:Python4k2514238

• eureka-research/Eureka

  Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

  Language:Jupyter Notebook2.8k2539258

• TransformerLensOrg/TransformerLens

  A library for mechanistic interpretability of GPT-style language models

  Language:Python1.6k17258307

• astoilkov/main-thread-scheduling

  Fast and consistently responsive apps using a single function call

  Language:TypeScript1.3k91433

• sdan/vlite

  fast vector database made in numpy

  Language:Python74582839

• minosvasilias/godot-dodo

  Finetuning large language models for GDScript generation.

  Language:Python5357826

• google-deepmind/tracr

  Language:Python508151443

• cgsdev0/bash-stack

  modern web framework in bash

  Language:Shell4914148

• jbloomAus/SAELens

  Training Sparse Autoencoders on Language Models

  Language:Jupyter Notebook4827118127

• bsilverthorn/maccarone

  AI-managed code blocks in Python ⏪⏩

  Language:Python471627

• EleutherAI/sae

  Sparse autoencoders

  Language:Python34671449

• Mihaiii/llm_steer

  Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors

  Language:Python2036211

• mxbi/arckit

  Tools for working with the Abstraction & Reasoning Corpus

  Language:Python1595422

• xjdr-alt/simple_transformer

  Simple Transformer in Jax

  Language:Python1192012

• arXiv/arxiv-browse

  Flask app for article abstract and listing pages

  Language:Python118172263

• neelnanda-io/1L-Sparse-Autoencoder

  Language:Python1082111

• abacaj/train-with-fsdp

  Language:Python914110

• lumpenspace/raft

  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 specific human target.

  Language:Python75108

• taylorai/onnx_embedding_models

  utilities for loading and running text embeddings with onnx

  Language:Python39114

• shehper/sparse-dictionary-learning

  An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"

  Language:Python29102

• teltam/twinkgrad

  Language:Rust6100

• wjessup/handmade-transformer

  making GPT2 transformer weights by hand

  Language:Python6101

• jhnwnstd/corpus_toolkit

  Python toolkit for corpus analysis: tokenization, lexical diversity, vocabulary growth prediction, entropy measures, and Zipf/Heaps visualizations.

  Language:Python5100