facebookresearch / matrixLinks
Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generation.
☆92Updated this week
Alternatives and similar repositories for matrix
Users that are interested in matrix are comparing it to the libraries listed below
Sorting:
- Source code for the collaborative reasoner research project at Meta FAIR.☆102Updated 4 months ago
- Code for ExploreTom☆86Updated 2 months ago
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖☆75Updated 9 months ago
- accompanying material for sleep-time compute paper☆108Updated 4 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 7 months ago
- ☆54Updated 10 months ago
- Train, tune, and infer Bamba model☆131Updated 3 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆88Updated 3 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆182Updated 6 months ago
- ☆133Updated 5 months ago
- ☆135Updated 3 weeks ago
- ☆80Updated last week
- Train your own SOTA deductive reasoning model☆106Updated 6 months ago
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆116Updated last month
- Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research☆225Updated this week
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆77Updated 5 months ago
- LLM reads a paper and produce a working prototype☆57Updated 5 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆24Updated last week
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆96Updated 2 weeks ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- ☆56Updated 2 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- Analysis code for paper "SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks"☆51Updated last month
- ☆68Updated 3 months ago
- Simple GRPO scripts and configurations.☆59Updated 7 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆291Updated 3 weeks ago
- EvaByte: Efficient Byte-level Language Models at Scale☆109Updated 4 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆49Updated 4 months ago
- Verifiers for LLM Reinforcement Learning☆72Updated 5 months ago
- ☆118Updated last year