evintunador / next-concept-predictorLinks
a WIP architecture designed to allow transformers to think in a manner without tokens
☆20Updated last year
Alternatives and similar repositories for next-concept-predictor
Users that are interested in next-concept-predictor are comparing it to the libraries listed below
Sorting:
- ☆40Updated last year
- Verbosity control for AI agents☆66Updated last year
- ☆45Updated 2 years ago
- ☆125Updated last year
- Port of Andrej Karpathy's nanoGPT to Apple MLX framework.☆116Updated last year
- Writing Blog Posts with Generative Feedback Loops!☆50Updated last year
- Mixing Language Models with Self-Verification and Meta-Verification☆111Updated last year
- ☆86Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆70Updated 2 years ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 2 months ago
- look how they massacred my boy☆63Updated last year
- Simple GRPO scripts and configurations.☆59Updated 11 months ago
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆34Updated 8 months ago
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆107Updated 3 months ago
- A library for benchmarking the Long Term Memory and Continual learning capabilities of LLM based agents. With all the tests and code you…☆82Updated last year
- A DSPy-based implementation of the tree of thoughts method (Yao et al., 2023) for generating persuasive arguments☆96Updated 3 months ago
- Explore the use of DSPy for extracting features from PDFs 🔎☆49Updated last year
- A framework for orchestrating AI agents using a mermaid graph☆77Updated last year
- DSPy program/pipeline inspector widget for Jupyter/VSCode Notebooks.☆43Updated last year
- Chat Markup Language conversation library☆55Updated 2 years ago
- Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"☆63Updated 9 months ago
- Track the progress of LLM context utilisation☆55Updated 8 months ago
- LLM reads a paper and produce a working prototype☆60Updated 8 months ago
- A reading list of relevant papers and projects on foundation model annotation☆28Updated 10 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆64Updated 8 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆91Updated 11 months ago
- a pipeline for using api calls to agnostically convert unstructured data into structured training data☆32Updated last year
- ☆53Updated 10 months ago
- A strongly typed Python DSL for developing message passing multi agent systems☆53Updated last year
- An attribution library for LLMs☆46Updated last year