ethan-w-roland / AUNNLinks
Simple implementation of Gwern's AUNN proposal
☆14Updated 3 months ago
Alternatives and similar repositories for AUNN
Users that are interested in AUNN are comparing it to the libraries listed below
Sorting:
- Simple Transformer in Jax☆142Updated last year
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆218Updated last year
- ☆66Updated 2 years ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆183Updated 2 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆198Updated last year
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆286Updated last year
- ☆214Updated 3 weeks ago
- The history files when recording human interaction while solving ARC tasks☆117Updated last week
- 8-bit computational substrates☆47Updated last year
- Extract full next-token probabilities via language model APIs☆248Updated last year
- ☆37Updated last month
- Aidan Bench attempts to measure <big_model_smell> in LLMs.☆315Updated 7 months ago
- smol models are fun too☆93Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆133Updated 3 years ago
- Draw more samples☆198Updated last year
- Resources from the EleutherAI Math Reading Group☆54Updated 11 months ago
- ☆29Updated last year
- ☆152Updated 4 months ago
- ☆85Updated last year
- A Loom implementation in Obsidian☆322Updated 10 months ago
- An interactive exploration of Transformer programming.☆271Updated 2 years ago
- ☆53Updated 2 years ago
- Minimal GPT (~350 lines with a simple task to test it)☆63Updated 2 months ago
- ☆76Updated last year
- ☆289Updated last year
- Grounding LLM mathematical reasoning with proof assistants.☆64Updated 2 years ago
- ☆47Updated 8 months ago
- Ultra low overhead NVIDIA GPU telemetry plugin for telegraf with memory temperature readings.☆63Updated last year
- explore token trajectory trees on instruct and base models☆150Updated 8 months ago
- seqax = sequence modeling + JAX☆170Updated 6 months ago