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
- A DSPy-based implementation of the tree of thoughts method (Yao et al., 2023) for generating persuasive arguments☆89Updated last week
- A collection of lightweight interpretability scripts to understand how LLMs think☆56Updated 2 weeks ago
- Simple GRPO scripts and configurations.☆59Updated 8 months ago
- ☆88Updated last year
- ☆46Updated 2 years ago
- LLM reads a paper and produce a working prototype☆57Updated 6 months ago
- Mixing Language Models with Self-Verification and Meta-Verification☆109Updated 10 months ago
- Port of Andrej Karpathy's nanoGPT to Apple MLX framework.☆112Updated last year
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆54Updated 5 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆91Updated 8 months ago
- Writing Blog Posts with Generative Feedback Loops!☆50Updated last year
- Simple Graph Memory for AI applications☆89Updated 4 months ago
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆104Updated 3 weeks ago
- An attribution library for LLMs☆42Updated last year
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆98Updated 2 months ago
- Verbosity control for AI agents☆65Updated last year
- look how they massacred my boy☆63Updated 11 months ago
- Train your own SOTA deductive reasoning model☆107Updated 7 months ago
- Based on the tree of thoughts paper☆48Updated 2 years ago
- Automating enterprise workflows with multimodal agents☆112Updated last year
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆34Updated 5 months ago
- ☆123Updated last year
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)☆87Updated last month
- An automated tool for discovering insights from research papaer corpora☆139Updated last year
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆102Updated last year
- A framework for orchestrating AI agents using a mermaid graph☆77Updated last year
- Very minimal (and stateless) agent framework☆45Updated 9 months ago
- ☆56Updated last week
- An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.☆32Updated last year