rl from zero pretrain, can it be done? yes.
☆292Sep 28, 2025Updated 7 months ago
Alternatives and similar repositories for avataRL
Users that are interested in avataRL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆32Jun 5, 2025Updated 10 months ago
- research impl of Native Sparse Attention (2502.11089)☆63Feb 19, 2025Updated last year
- ☆15Apr 26, 2025Updated last year
- Approximating the joint distribution of language models via MCTS☆22Nov 3, 2024Updated last year
- Entropy Based Sampling and Parallel CoT Decoding☆17Oct 9, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆609Oct 7, 2025Updated 6 months ago
- Exploring Applications of GRPO☆252Aug 25, 2025Updated 8 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Apr 22, 2025Updated last year
- Our library for RL environments + evals☆4,057Updated this week
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,406Apr 17, 2026Updated 2 weeks ago
- Agentic RL Training at Scale☆1,323Updated this week
- ☆90Aug 16, 2025Updated 8 months ago
- a high-quality, GPU-accelerated image resizer☆14Mar 6, 2025Updated last year
- Simple repository for training small reasoning models☆50Feb 17, 2026Updated 2 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Entropy Based Sampling and Parallel CoT Decoding☆3,431Nov 13, 2024Updated last year
- Educational WIP☆70Feb 16, 2026Updated 2 months ago
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆104Jul 19, 2025Updated 9 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,248Aug 27, 2025Updated 8 months ago
- ☆148Sep 29, 2025Updated 7 months ago
- Cerule - A Tiny Mighty Vision Model☆69Nov 9, 2025Updated 5 months ago
- UB ImGui (Unity Better ImGui) is a binding of "Dear ImGui" for Unity. It allows you to create interfaces by code, in immediate mode, in a…☆15Sep 10, 2025Updated 7 months ago
- ☆39Aug 4, 2025Updated 8 months ago
- alternative way to calculating self attention☆18May 25, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Aioli: A unified optimization framework for language model data mixing☆32Jan 17, 2025Updated last year
- A simple, performant and scalable JAX-based world modeling codebase.☆145Jan 15, 2026Updated 3 months ago
- CleanVul: Automatic Function-Level Vulnerability Detection in Code Commits Using LLM Heuristics☆22Mar 25, 2026Updated last month
- EvaByte: Efficient Byte-level Language Models at Scale☆117Apr 22, 2025Updated last year
- hakken is a coding agent which needs hell lot of context☆31Dec 4, 2025Updated 4 months ago
- Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"☆11Jan 10, 2025Updated last year
- Culturally-compliant video storage. Embeds searchable text chunks into pixelated media for lightning-fast semantic search. Zero-database,…☆21Jun 8, 2025Updated 10 months ago
- Mention any three favourite things and get recommendations in the form of a flow chart by Claude Haiku.☆14Apr 6, 2024Updated 2 years ago
- Agentkube - Run Kubernetes Like Never Before☆38Mar 1, 2026Updated 2 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆20Updated this week
- NanoGPT (124M) in 90 seconds☆5,157Updated this week
- Softened ROSA QKV Operators for Training Next-Generation LLM Models☆36Apr 7, 2026Updated 3 weeks ago
- Code for☆28Dec 16, 2024Updated last year
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆342Jan 5, 2026Updated 3 months ago
- Storing long contexts in tiny caches with self-study☆262Mar 23, 2026Updated last month
- Lightly-reviewed collection of community environments☆226Apr 7, 2026Updated 3 weeks ago