yizhe-ang / interactive-transformer
A visual interface for understanding and interpreting Transformers
☆76Updated last year
Related projects ⓘ
Alternatives and complementary repositories for interactive-transformer
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆60Updated 5 months ago
- Simple Transformer in Jax☆115Updated 4 months ago
- Simple embedding -> text model trained on a small subset of Wikipedia sentences.☆152Updated last year
- Sparse autoencoders for Contra text embedding models☆24Updated 6 months ago
- The history files when recording human interaction while solving ARC tasks☆94Updated this week
- look how they massacred my boy☆53Updated 3 weeks ago
- Stream of my favorite papers and links☆36Updated 2 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆22Updated last month
- Navigating a maze using LLM agent☆34Updated last year
- papers.day☆79Updated 10 months ago
- A replication of Andy Ayrey's "Backrooms" (https://dreams-of-an-electric-mind.webflow.io/), but runnable with Opus 3, Sonnet 3.5, GPT 4o,…☆69Updated this week
- Cerule - A Tiny Mighty Vision Model☆67Updated 2 months ago
- A puzzle to learn about prompting☆119Updated last year
- compute, storage, and networking infra at home☆63Updated 8 months ago
- ☆13Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated 10 months ago
- ☆48Updated last year
- Aidan Bench attempts to measure <big_model_smell> in LLMs.☆89Updated 3 weeks ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆151Updated this week
- A repository of prompts and Python scripts for intelligent transformation of raw text into diverse formats.☆29Updated last year
- Simplex Random Feature attention, in PyTorch☆71Updated last year
- This repository explains and provides examples for "concept anchoring" in GPT4.☆72Updated 10 months ago
- ☆99Updated 3 months ago
- direct preference optimization with only 1 model copy :)☆12Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- ☆142Updated last year
- Drive a browser with Cohere☆72Updated last year
- A synthetic story narration dataset to study small audio LMs.☆29Updated 9 months ago
- KMD is a collection of conversational exchanges between patients and doctors on various medical topics. It aims to capture the intricaci…☆23Updated 11 months ago
- they've simulated websites, worlds, and imaginary CLIs... but what if they simulated *you*?☆90Updated 3 weeks ago