vgel / logitloomLinks
explore token trajectory trees on instruct and base models
☆150Updated 8 months ago
Alternatives and similar repositories for logitloom
Users that are interested in logitloom are comparing it to the libraries listed below
Sorting:
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆77Updated last year
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 4 months ago
- look how they massacred my boy☆63Updated last year
- Approximating the joint distribution of language models via MCTS☆22Updated last year
- A graph visualization of attention☆57Updated 8 months ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated last year
- Plotting (entropy, varentropy) for small LMs☆99Updated 8 months ago
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆85Updated 5 months ago
- Official CLI and Python SDK for Prime Intellect - access GPU compute, remote sandboxes, RL environments, and distributed training infrast…☆151Updated this week
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆61Updated last year
- smol models are fun too☆93Updated last year
- ☆304Updated 3 months ago
- PageRank for LLMs☆52Updated 5 months ago
- smolLM with Entropix sampler on pytorch☆149Updated last year
- ☆67Updated 8 months ago
- Train your own SOTA deductive reasoning model☆107Updated 11 months ago
- ☆73Updated last week
- A framework for optimizing DSPy programs with RL☆313Updated 3 weeks ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆150Updated last month
- Storing long contexts in tiny caches with self-study☆236Updated 2 months ago
- Simple Transformer in Jax☆142Updated last year
- ☆40Updated last year
- Pivotal Token Search☆144Updated last month
- An introduction to LLM Sampling☆79Updated last year
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆134Updated this week
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆102Updated 6 months ago
- Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.☆58Updated last year
- cli loom that uses git to manage branches☆32Updated last year
- rl from zero pretrain, can it be done? yes.☆286Updated 4 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆110Updated 11 months ago