Dicklesworthstone / llm_introspective_compression_and_metacognition
A novel approach for transformer model introspection that enables saving, compressing, and manipulating internal thought states for advanced capabilities like reasoning backtracking, latent thought optimization, and metacognitive control.
☆19Updated last month
Alternatives and similar repositories for llm_introspective_compression_and_metacognition
Users that are interested in llm_introspective_compression_and_metacognition are comparing it to the libraries listed below
Sorting:
- Local LLM inference & management server with built-in OpenAI API☆31Updated last year
- ☆16Updated last year
- A text-to-SQL prototype on the northwind sqlite dataset☆12Updated 7 months ago
- A task management system designed for AI development☆18Updated this week
- LLM Divergent Thinking Creativity Benchmark. LLMs generate 25 unique words that start with a given letter with no connections to each oth…☆32Updated last month
- 🧩 Optimal Chunk Size for Large Document Summarization☆22Updated last year
- A clone of OpenAI's Tokenizer page for HuggingFace Models☆45Updated last year
- The GitHub webhooks you deserve github-webhooks, vibe-coding☆4Updated 3 weeks ago
- Light WebUI for lm.rs☆23Updated 7 months ago
- Prompt-based software development☆23Updated 8 months ago
- ☆16Updated 8 months ago
- Attend - to what matters.☆15Updated 2 months ago
- Training hybrid models for dummies.☆21Updated 4 months ago
- LLM code editor for backend services☆14Updated 6 months ago
- Yet Another (LLM) Web UI, made with Gemini☆12Updated 4 months ago
- A daemon that makes a desktop OS accessible to AI agents☆26Updated this week
- Build HTML artefacts with Ollama☆11Updated 5 months ago
- 🛠 Self-hosted, fast, and consistent remote configuration for apps.☆15Updated 2 years ago
- ☆27Updated 8 months ago
- convert natural language into technical diagrams☆14Updated 5 months ago
- An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.☆26Updated 10 months ago
- ☆23Updated 6 months ago
- A Python framework for building AI agent systems with robust task management in the form of a graph execution engine, inference capabilit…☆25Updated this week
- A star for organising blocks and playing with transformers.☆23Updated last year
- Run Llama 2 using MLX on macOS☆34Updated last year
- With a few words and a click of a button, quickly get an engaging, high quality video. (And optionally save and share it!)☆17Updated last week
- Using modal.com to process FineWeb-edu data☆20Updated last month
- an AI powered application that makes it simple to go from experimentation to automation.☆21Updated last week
- A lightweight Python utility that aggregates and exports comprehensive system information to JSON, specifically designed for feeding syst…☆13Updated last month
- The original BabyAGI, updated with LiteLLM and no vector database reliance (csv instead)☆21Updated 7 months ago