facebookresearch / searchformerLinks
Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".
☆374Updated last year
Alternatives and similar repositories for searchformer
Users that are interested in searchformer are comparing it to the libraries listed below
Sorting:
- LLM verified with Monte Carlo Tree Search☆284Updated 9 months ago
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆628Updated 9 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆658Updated 7 months ago
- a curated list of data for reasoning ai☆140Updated last year
- ☆177Updated last month
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆218Updated last year
- Visualize the intermediate output of Mistral 7B☆381Updated 11 months ago
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆287Updated 3 months ago
- Grandmaster-Level Chess Without Search☆599Updated 11 months ago
- ☆250Updated last year
- Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind☆405Updated 6 months ago
- Pytorch script hot swap: Change code without unloading your LLM from VRAM☆125Updated 8 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆345Updated last year
- ☆252Updated 10 months ago
- GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's T…☆319Updated 4 months ago
- Diffusion on syntax trees for program synthesis☆479Updated last year
- A pure NumPy implementation of Mamba.☆222Updated last year
- LLM Analytics☆700Updated last year
- Cost aware hyperparameter tuning algorithm☆177Updated last year
- Easily train AlphaZero-like agents on any environment you want!☆433Updated last year
- DiscoGrad - automatically differentiate across conditional branches in C++ programs☆209Updated last year
- An implementation of bucketMul LLM inference☆223Updated last year
- Autograd to GPT-2 completely from scratch☆125Updated 4 months ago
- LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.☆666Updated 4 months ago
- Fine-tune LLM agents with online reinforcement learning☆1,247Updated last year
- ☆460Updated last month
- Controlled Text Generation via Language Model Arithmetic☆224Updated last year
- A tool to analyze and debug neural networks in pytorch. Use a GUI to traverse the computation graph and view the data from many different…☆298Updated last year
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆254Updated 2 years ago
- Long context evaluation for large language models☆225Updated 10 months ago