Thinking Like Transformers arxiv.org ↗

Recommended in 0 threads

Similar tools

• 
  Tracr ↗AI & ML

  DeepMind's compiler that turns RASP programs into transformer weights for interpretability research.

  1 thread
• L
  llm AI & ML

  A command-line tool for prompting various language models.

  1 thread
• 
  Terra 6.1 ↗AI & ML

  A large language model in the Terra series.

  0 threads
• 
  Hutter Prize ↗AI & ML

  A prize for losslessly compressing English Wikipedia, built on the premise that compression is a measure of intelligence.

  1 thread
• 
  DeepSeek ↗AI & ML

  A family of large language models offered via a low-cost API.

  12 threads
• 
  XGrammar ↗AI & ML

  A library for efficient grammar-constrained structured generation in LLM inference.

  1 thread
• 
  DeepSeek 4.1 Flash ↗AI & ML

  An open-weight language model from DeepSeek.

  0 threads
• 
  Physical Intelligence API ↗AI & ML

  A beta API from Physical Intelligence for running its robot foundation models, fine-tuned per task and robot.

  1 thread

Also in AI & ML

• 
  OpenRouter ↗

  A marketplace that routes API requests to many LLM inference providers.

  19 threads
• 
  DeepSeek ↗

  A family of large language models offered via a low-cost API.

  12 threads
• 
  llama.cpp ↗

  A C/C++ engine for running LLMs locally.

  12 threads
• 
  GLM ↗

  An open-weights large language model family from Zhipu AI.

  11 threads
• 
  Qwen ↗

  Alibaba's family of open-weight large language models.

  9 threads
• 
  DeepSeek V4.1 Flash ↗

  A low-cost DeepSeek language model available via API.

  8 threads
• 
  Artificial Analysis ↗

  A site benchmarking and comparing AI models on quality, price and speed.

  7 threads
• 
  Claude ↗

  Anthropic's AI model and command-line assistant.

  7 threads
• 
  Qwen 3.8 Flash Next ↗

  A Qwen open-weight model that can be run locally.

  5 threads
• 
  Strata ↗

  An open-source project for running large MoE models on small-VRAM GPUs with system RAM.

  5 threads
• 
  OpenCode Go ↗

  A subscription plan for accessing models through the OpenCode coding tool.

  4 threads
• 
  Pangram ↗

  A service that uses a trained model to detect AI-generated text.

  4 threads