Dicklesworthstone / llm_introspective_compression_and_metacognitionLinks
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.
☆26Updated 4 months ago
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:
- Pivotal Token Search☆121Updated last month
- a lightweight, open-source blueprint for building powerful and scalable LLM chat applications☆28Updated last year
- Lego for GRPO☆29Updated 3 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆146Updated 6 months ago
- Approximating the joint distribution of language models via MCTS☆21Updated 9 months ago
- ☆59Updated last month
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 9 months ago
- Accompanying code and SEP dataset for the "Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?" paper.☆54Updated 5 months ago
- An AI character interaction system with emotional modeling and advanced memory management☆16Updated 10 months ago
- utilities for loading and running text embeddings with onnx☆44Updated last week
- entropix style sampling + GUI☆27Updated 9 months ago
- A library for building software agents using behavior trees and language models.☆86Updated 6 months ago
- Aana SDK is a powerful framework for building AI enabled multimodal applications.☆52Updated last week
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 6 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆32Updated 6 months ago
- A Python library to orchestrate LLMs in a neural network-inspired structure☆50Updated 10 months ago
- look how they massacred my boy☆64Updated 10 months ago
- Benchmark that evaluates LLMs using 651 NYT Connections puzzles extended with extra trick words☆136Updated this week
- "a towel is about the most massively useful thing an interstellar AI hitchhiker can have"☆48Updated 10 months ago
- Latent Large Language Models☆18Updated last year
- Clue inspired puzzles for testing LLM deduction abilities☆40Updated 5 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆92Updated 7 months ago
- explore token trajectory trees on instruct and base models☆133Updated 3 months ago
- ☆67Updated last year
- LLM Divergent Thinking Creativity Benchmark. LLMs generate 25 unique words that start with a given letter with no connections to each oth…☆33Updated 5 months ago
- ☆28Updated last year
- Modified Beam Search with periodical restart☆12Updated 11 months ago
- ☆39Updated last year
- OpenPipe Reinforcement Learning Experiments☆30Updated 5 months ago
- Simple LLM inference server☆20Updated last year