trl repositories

Trending repositories tagged trl, ranked by trending score. Updated daily.

  1. 1
    ChaitanyaK77/Verifiable-Reasoning-Post-Training-for-Qwen3-8B

    Single-GPU post-training pipeline for Qwen3-8B math reasoning. Combines QLoRA SFT, DPO, and GRPO with verifiable rewards (correctness + format + length). Seven Colab notebooks, +6pp GSM8K from SFT alone

    GitHub · Jupyter Notebook · 7 stars · 0 forks · +2 stars in 24 hours · Trending score 0.73

  2. 2
    mem-audit/memaudit

    Training-data memorization auditor for fine-tuned LLMs — Trainer/TRL plugin, canary MIA + regurgitation audit, Apache-2.0

    GitHub · Python · 14 stars · 0 forks · +1 stars in 24 hours · Trending score 0.46

  3. 3
    adithya-s-k/FineEnvs

    FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs

    GitHub · Python · 563 stars · 78 forks · 0 stars in 24 hours · Trending score 0.42

  4. 4
    DeepGym/deepgym

    RL environments with verifiable rewards you can trust. Sandboxed coding and computer-use tasks, verifiers kept apart from the answer, a QA gate against reward hacking, and infra failures kept out of training. Works with verl, TRL, OpenRLHF and Axolotl.

    GitHub · Python · 22 stars · 5 forks · −3 stars in 24 hours · Trending score 0.18

  5. 5
    Zihao-Wu06/distillops

    Black-box LLM distillation for any verifiable task, with text or image inputs: teacher API -> rejection sampling -> SFT -> eval -> GRPO

    GitHub · Python · 58 stars · 4 forks · −45 stars in 24 hours · Trending score 0.16

  6. 6
    amortized-ai/amortized

    Build task models that replace frontier API calls

    GitHub · Python · 11 stars · 4 forks · 0 stars in 24 hours · Trending score 0.09

  7. 7
    HodeTech/ForgeLM

    Config-driven LLM fine-tuning with safety evaluation, EU AI Act compliance, 6 alignment methods, and one-command bundled quickstart templates.

    GitHub · Python · 9 stars · 12 forks · 0 stars in 24 hours · Trending score 0.04

  8. 8
    Sheltercosmo/Rilldex-RL-Studio

    RL observability for LLM agents: behavior maps, native trainer metrics, rollout investigations, and Python/SQL analysis.

    GitHub · Python · 80 stars · 17 forks · 0 stars in 24 hours · Trending score 0.00

  9. 9
    cookiespiggy/agentic-rl

    Agentic RL 中文零基础教程(33 章):从概念到 GRPO 实战,含 TRL 最小可跑示例;26–33 章附一套可运行的三方判别模型实证工程(encoder vs LLM-LoRA vs 规则基线)。第 25 章讲清 Jev / TypeSafe System One 与 RL 的能力边界 | Chinese Agentic RL tutorial (33 chapters) + a reproducible discriminative-model benchmark

    GitHub · Python · 126 stars · 13 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    cainiao33/Qwen-Cup-Multimodal-RL

    Qwen Cup multimodal reasoning competition (20/337 → finals 9/20 → defense 3rd 🏆): teacher-distillation SFT + small-dose GRPO RL on Qwen3.5-0.8B, reward-eval verbatim alignment, full data engineering & ablation chain

    GitHub · Python · 12 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00