valine / training-hot-swapLinks
Pytorch script hot swap: Change code without unloading your LLM from VRAM
☆124Updated 7 months ago
Alternatives and similar repositories for training-hot-swap
Users that are interested in training-hot-swap are comparing it to the libraries listed below
Sorting:
- A character-level language diffusion model trained on Tiny Shakespeare☆565Updated last week
- ☆455Updated 3 weeks ago
- ☆248Updated last year
- Heirarchical Navigable Small Worlds☆101Updated 3 months ago
- ☆198Updated 6 months ago
- Pivotal Token Search☆131Updated 4 months ago
- ☆241Updated 8 months ago
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆286Updated 2 months ago
- DiscoGrad - automatically differentiate across conditional branches in C++ programs☆208Updated last year
- High-Performance Implementation of OpenAI's TikToken.☆460Updated 4 months ago
- ☆47Updated 7 months ago
- An implementation of bucketMul LLM inference☆223Updated last year
- A tiny autograd engine with a Jax-like API☆74Updated 4 months ago
- A playground to make it easy to try crazy things☆33Updated last month
- A pure NumPy implementation of Mamba.☆223Updated last year
- Code for the Fractured Entangled Representation Hypothesis position paper!☆206Updated 2 weeks ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆375Updated last year
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆219Updated last year
- a curated list of data for reasoning ai☆140Updated last year
- Autograd to GPT-2 completely from scratch☆125Updated 3 months ago
- lossily compress representation vectors using product quantization☆59Updated 3 weeks ago
- explore token trajectory trees on instruct and base models☆148Updated 5 months ago
- Live-bending a foundation model’s output at neural network level.☆270Updated 7 months ago
- Dead Simple LLM Abliteration☆239Updated 9 months ago
- Docker-based inference engine for AMD GPUs☆230Updated last year
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆254Updated 2 years ago
- Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems☆106Updated 7 months ago
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆624Updated 8 months ago
- Tensor library & inference framework for machine learning☆113Updated last month
- Alice in Wonderland code base for experiments and raw experiments data☆131Updated 2 months ago