namin / llm-verified-with-monte-carlo-tree-search
LLM verified with Monte Carlo Tree Search
☆270Updated last month
Alternatives and similar repositories for llm-verified-with-monte-carlo-tree-search:
Users that are interested in llm-verified-with-monte-carlo-tree-search are comparing it to the libraries listed below
- LLMs + Lean, on your laptop or in the cloud☆138Updated 5 months ago
- a curated list of data for reasoning ai☆132Updated 7 months ago
- Retrieval-Augmented Theorem Provers for Lean☆261Updated last month
- LeanUniverse: A Library for Consistent and Scalable Lean4 Dataset Management☆59Updated 2 months ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆365Updated 9 months ago
- Tutorial on neural theorem proving☆166Updated last year
- Harmonic Datasets☆36Updated 8 months ago
- llmstep: [L]LM proofstep suggestions in Lean 4.☆127Updated last year
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆202Updated 4 months ago
- The official repository for the paper Multilingual Mathematical Autoformalization☆34Updated 10 months ago
- LILO: Library Induction with Language Observations☆84Updated 6 months ago
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆248Updated 4 months ago
- Extract full next-token probabilities via language model APIs☆233Updated last year
- Learning Universal Predictors☆76Updated 7 months ago
- Formalizing stochastic doubly-efficient debate☆100Updated 5 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆142Updated last month
- An updated version of miniF2F with lots of fixes and informal statements / solutions.☆77Updated 2 months ago
- a categorical deep learning compiler☆199Updated 3 weeks ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆186Updated 9 months ago
- Benchmark for undergraduate-level formal mathematics☆103Updated 5 months ago
- Neural theorem proving tutorial, version II☆34Updated 10 months ago
- ChatGPT plugin for theorem proving in Lean☆116Updated 11 months ago
- An evaluation benchmark for undergraduate competition math in Lean4, Isabelle, Coq, and natural language.☆93Updated last week
- LeanEuclid is a benchmark for autoformalization in the domain of Euclidean geometry, targeting the proof assistant Lean.☆87Updated 9 months ago
- An environment for learning formal mathematical reasoning from scratch☆65Updated 7 months ago
- Controlled Text Generation via Language Model Arithmetic☆216Updated 6 months ago
- Can Language Models Solve Olympiad Programming?☆112Updated 2 months ago
- Our solution for the arc challenge 2024☆110Updated 3 weeks ago