facebookresearch / matrixLinks
Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generation.
☆88Updated 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.☆101Updated 4 months ago
- Code for ExploreTom☆85Updated 2 months ago
- accompanying material for sleep-time compute paper☆105Updated 3 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 6 months ago
- Train your own SOTA deductive reasoning model☆104Updated 5 months ago
- ☆54Updated 9 months ago
- ☆130Updated 5 months ago
- ☆77Updated last week
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖☆73Updated 8 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆177Updated 5 months ago
- Train, tune, and infer Bamba model☆131Updated 2 months ago
- ☆55Updated 2 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆73Updated 5 months ago
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆117Updated 2 weeks ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 7 months ago
- Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research☆223Updated this week
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆92Updated 7 months ago
- Verifiers for LLM Reinforcement Learning☆70Updated 4 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆83Updated 3 months ago
- ☆120Updated 6 months ago
- Analysis code for paper "SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks"☆47Updated 2 weeks ago
- ☆34Updated 3 weeks ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆46Updated 3 months ago
- ☆134Updated this week
- The first dense retrieval model that can be prompted like an LM☆83Updated 3 months ago
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆61Updated 8 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated 11 months ago
- KV Cache Steering for Inducing Reasoning in Small Language Models☆39Updated last month
- The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆94Updated last month
- ☆49Updated 9 months ago