valine / training-hot-swapLinks
Pytorch script hot swap: Change code without unloading your LLM from VRAM
☆125Updated 5 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:
- ☆417Updated 3 weeks ago
- Heirarchical Navigable Small Worlds☆101Updated last month
- A tiny autograd engine with a Jax-like API☆74Updated 2 months ago
- ☆247Updated last year
- ☆230Updated 6 months ago
- ☆196Updated 4 months ago
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆285Updated last week
- Pivotal Token Search☆125Updated 2 months ago
- GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's T…☆254Updated 3 weeks ago
- A playground to make it easy to try crazy things☆33Updated 3 months ago
- Autograd to GPT-2 completely from scratch☆125Updated last month
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆213Updated 10 months ago
- ☆47Updated 5 months ago
- DiscoGrad - automatically differentiate across conditional branches in C++ programs☆206Updated last year
- An implementation of bucketMul LLM inference☆223Updated last year
- ☆209Updated this week
- High-Performance Implementation of OpenAI's TikToken.☆451Updated 2 months ago
- Live-bending a foundation model’s output at neural network level.☆265Updated 5 months ago
- Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems☆105Updated 5 months ago
- A library for incremental loading of large PyTorch checkpoints☆56Updated 2 years ago
- Simple high-throughput inference library☆127Updated 4 months ago
- Mistral7B playing DOOM☆136Updated last year
- Dead Simple LLM Abliteration☆231Updated 7 months ago
- A pure NumPy implementation of Mamba.☆224Updated last year
- a curated list of data for reasoning ai☆137Updated last year
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆98Updated 2 months ago
- SIMD quantization kernels☆87Updated 2 weeks ago
- Alice in Wonderland code base for experiments and raw experiments data☆131Updated this week
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆373Updated last year
- Tensor library & inference framework for machine learning☆110Updated 3 weeks ago