NousResearch / atropos
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
☆171Updated this week
Alternatives and similar repositories for atropos:
Users that are interested in atropos are comparing it to the libraries listed below
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 3 months ago
- ☆123Updated last month
- Train your own SOTA deductive reasoning model☆91Updated last month
- ☆109Updated 4 months ago
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆437Updated 7 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆98Updated last month
- smolLM with Entropix sampler on pytorch☆151Updated 6 months ago
- Verdict is a library for scaling judge-time compute.☆202Updated this week
- Compiling useful links, papers, benchmarks, ideas, etc.☆46Updated last month
- prime-rl is a codebase for decentralized RL training at scale☆85Updated this week
- ☆97Updated 6 months ago
- ⚖️ Awesome LLM Judges ⚖️☆94Updated last week
- procedural reasoning datasets☆573Updated this week
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆139Updated 2 months ago
- smol models are fun too☆92Updated 5 months ago
- Build your own visual reasoning model☆357Updated this week
- 🤗 Benchmark Large Language Models Reliably On Your Data☆281Updated this week
- Fast parallel LLM inference for MLX☆186Updated 9 months ago
- ☆151Updated 5 months ago
- Exploring Applications of GRPO☆189Updated this week
- DeMo: Decoupled Momentum Optimization☆186Updated 5 months ago
- look how they massacred my boy☆63Updated 6 months ago
- ☆171Updated 3 weeks ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆172Updated last month
- Simple Transformer in Jax☆136Updated 10 months ago
- ☆129Updated 8 months ago
- A repository to unravel the language of GPUs, making their kernel conversations easy to understand☆180Updated last week
- code for training & evaluating Contextual Document Embedding models☆183Updated 2 weeks ago
- ☆130Updated last month
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym☆448Updated last month