Skip to content
View vgel's full-sized avatar

Block or report vgel

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

visualizing attention for LLM users

Python 182 8 Updated Dec 14, 2024
Python 2,200 252 Updated Dec 20, 2024
JavaScript 16 1 Updated Dec 2, 2024

Advanced Search for Twitter.

1,281 98 Updated Jan 31, 2024
TypeScript 10 1 Updated Oct 10, 2024

small games

JavaScript 1 Updated Jan 19, 2023

Entropy Based Sampling and Parallel CoT Decoding

Python 3,178 317 Updated Nov 13, 2024

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

Python 745 38 Updated Dec 10, 2024

A vector search SQLite extension that runs anywhere!

C 4,546 154 Updated Nov 26, 2024

LLM101n: Let's build a Storyteller

30,726 1,677 Updated Aug 1, 2024

Simple Transformer in Jax

Python 120 12 Updated Jun 22, 2024

Sparse autoencoders

Python 390 51 Updated Dec 18, 2024
Rust 7 Updated Jun 23, 2024

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

Python 34 3 Updated May 12, 2024

Training Sparse Autoencoders on Language Models

Jupyter Notebook 545 132 Updated Dec 15, 2024

Solve puzzles. Learn CUDA.

Jupyter Notebook 10,214 965 Updated Sep 1, 2024

modern web framework in bash

Shell 550 8 Updated Dec 5, 2024

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 78 8 Updated Aug 31, 2024

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

Python 6 Updated Dec 21, 2024

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

Python 210 12 Updated May 11, 2024

utilities for loading and running text embeddings with onnx

Python 40 4 Updated Aug 6, 2024

Fast and consistently responsive apps using a single function call

TypeScript 1,316 34 Updated Aug 7, 2024

making GPT2 transformer weights by hand

Python 6 1 Updated Oct 17, 2023

Distribute and run LLMs with a single file.

C++ 21,024 1,081 Updated Dec 14, 2024

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

Jupyter Notebook 2,859 259 Updated May 3, 2024

Tools for working with the Abstraction & Reasoning Corpus

Python 170 23 Updated Aug 8, 2024

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

Python 20,542 1,551 Updated Dec 27, 2024
Python 91 10 Updated Oct 5, 2023
Next