Alternatives and similar repositories for logitloom

Users that are interested in logitloom are comparing it to the libraries listed below

• N8python / n8loom
  A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.
  ☆72Updated 7 months ago
• xjdr-alt / llmri
  look how they massacred my boy
  ☆63Updated 11 months ago
• samefarrar / entropix_mlx
  Modify Entropy Based Sampling to work with Mac Silicon via MLX
  ☆49Updated 11 months ago
• JD-P / RetroInstruct
  Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.
  ☆32Updated 7 months ago
• doomslide / autoloom
  Approximating the joint distribution of language models via MCTS
  ☆21Updated 11 months ago
• doomslide / hyperobject
  Plotting (entropy, varentropy) for small LMs
  ☆98Updated 4 months ago
• smolorg / smoltropix
  MLX port for xjdr's entropix sampler (mimics jax implementation)
  ☆62Updated 11 months ago
• N8python / mlx-pretrain
  A simple MLX implementation for pretraining LLMs on Apple Silicon.
  ☆83Updated last month
• doomslide / attention-graph
  A graph visualization of attention
  ☆57Updated 4 months ago
• xjdr-alt / entropix-local
  smol models are fun too
  ☆93Updated 10 months ago
• SpellcraftAI / turing
  Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.
  ☆58Updated last year
• HazyResearch / cartridges
  Storing long contexts in tiny caches with self-study
  ☆194Updated 3 weeks ago
• SinatrasC / entropix-smollm
  smolLM with Entropix sampler on pytorch
  ☆150Updated 11 months ago
• Mihaiii / backtrack_sampler
  An easy-to-understand framework for LLM samplers that rewind and revise generated tokens
  ☆146Updated 7 months ago
• PrimeIntellect-ai / prime-cli
  The Prime Intellect CLI provides a powerful command-line interface for managing GPU resources across various providers
  ☆93Updated last week
• haizelabs / Awesome-LLM-Judges
  ⚖️ Awesome LLM Judges ⚖️
  ☆130Updated 5 months ago
• haizelabs / j1-micro
  j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
  ☆98Updated 2 months ago
• qpwo / clod-code
  rot13 version of claudd code
  ☆40Updated 6 months ago
• sam-paech / slop-forensics
  ☆269Updated 3 months ago
• Ziems / arbor
  A framework for optimizing DSPy programs with RL
  ☆185Updated 2 weeks ago
• xjdr-alt / simple_transformer
  Simple Transformer in Jax
  ☆139Updated last year
• xjdr-alt / muzero_sketch
  ☆40Updated last year
• JD-P / minihf
  MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…
  ☆181Updated 2 months ago
• jxmorris12 / embzip
  lossily compress representation vectors using product quantization
  ☆59Updated 5 months ago
• normal-computing / extended-mind-transformers
  ☆123Updated last year
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆107Updated 7 months ago
• neurallambda / awesome-reasoning
  a curated list of data for reasoning ai
  ☆137Updated last year
• codelion / pts
  Pivotal Token Search
  ☆126Updated 2 months ago
• jxmorris12 / gptzip
  Losslessly encode text natively with arithmetic coding and HuggingFace Transformers
  ☆76Updated last year
• maxsloef / loom-mcp
  this is a TypeScript-based MCP server that implements a simple loom and makes it available for Claude to use.
  ☆21Updated 10 months ago