InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. verl-agent

    Agents & frameworks

    verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

    Stale GitHub, langfengQ 2,377 ★Apache-2.0Updated 5 months ago

    git clone https://github.com/langfengQ/verl-agent.git
  2. Nemotron-Post-Training-Dataset-v1

    Datasets & benchmarks

    Hugging Face dataset by nvidia

    Stale Hugging Face Hub, nvidia 197 ♥cc-by-4.0Updated 14 months ago

    nvidia/Nemotron-Post-Training-Dataset-v1
  3. AgileRL

    Agents & frameworks

    The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.

    Indexed GitHub, AgileRL 968 ★Apache-2.0Updated today

    git clone https://github.com/AgileRL/AgileRL.git
  4. agent-lightning

    AI repositories

    The absolute trainer to light up AI agents.

    Stale GitHub, microsoft 18.9k ★MITUpdated 4 days ago

    git clone https://github.com/microsoft/agent-lightning.git
  5. train_1M_CN

    Datasets & benchmarks

    Hugging Face dataset by BelleGroup

    Stale Hugging Face Hub, BelleGroup 161 ♥gpl-3.0Updated 3 years ago

    BelleGroup/train_1M_CN
  6. train_3.5M_CN

    Datasets & benchmarks

    Hugging Face dataset by BelleGroup

    Stale Hugging Face Hub, BelleGroup 160 ♥gpl-3.0Updated 3 years ago

    BelleGroup/train_3.5M_CN
  7. text generation model by HuggingFaceH4 · transformers

    Indexed Hugging Face Hub, HuggingFaceH4 1,868 ♥mitUpdated 2 years ago

    HuggingFaceH4/zephyr-7b-beta
  8. Libra

    Agents & frameworks

    Libra: Efficient Resource Management for Agentic RL Post-Training

    Stale GitHub, NetX-lab 284 ★MITUpdated 24 days ago

    git clone https://github.com/NetX-lab/Libra.git
  9. stack-v3-train

    Datasets & benchmarks

    Hugging Face dataset by HuggingFaceCode

    Indexed Hugging Face Hub, HuggingFaceCode 402 ♥odc-byUpdated 52 days ago

    HuggingFaceCode/stack-v3-train
  10. text generation model by HuggingFaceH4 · transformers

    Stale Hugging Face Hub, HuggingFaceH4 1,136 ♥mitUpdated 2 years ago

    HuggingFaceH4/zephyr-7b-alpha
  11. 12306-mcp

    MCP servers

    This is a 12306 ticket search server based on the Model Context Protocol (MCP).

    Stale GitHub, Joooook 2,381 ★MITUpdated 3 months ago

    git clone https://github.com/Joooook/12306-mcp.git
  12. SwanLab

    AI repositories

    ⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / Ultralytics / MMEngine / Keras etc.

    Indexed GitHub, SwanHubX 4,376 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/SwanHubX/SwanLab.git
  13. metaflow

    AI repositories

    Build, Manage and Deploy AI/ML Systems

    Stale GitHub, Netflix 10.3k ★Apache-2.0Updated 7 days ago

    git clone https://github.com/Netflix/metaflow.git
  14. OpenVid-1M

    Datasets & benchmarks

    Hugging Face dataset by nkp37

    Indexed Hugging Face Hub, nkp37 300 ♥cc-by-4.0Updated 7 months ago

    nkp37/OpenVid-1M
  15. heretic

    AI repositories

    Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more

    Indexed GitHub, p-e-w 40.6k ★AGPL-3.0Updated 2 days ago

    git clone https://github.com/p-e-w/heretic.git
  16. data-juicer

    AI repositories

    Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

    Indexed GitHub, datajuicer 7,250 ★Apache-2.0Updated today

    git clone https://github.com/datajuicer/data-juicer.git
  17. llm-datasets

    AI repositories

    Curated list of datasets and tools for post-training.

    Stale GitHub, mlabonne 4,809 ★Updated 6 months ago

    git clone https://github.com/mlabonne/llm-datasets.git
  18. llm-algo-leetcode

    Docs & tutorials

    Hands-on LLM algorithms and systems with PyTorch, Triton & CUDA.《大模型算法与系统教程》:模型架构与训练、后训练、推理加速、性能与算子优化,配套 Notebook 练习、答案解析、测试与实验。

    Indexed GitHub, datawhalechina 794 ★Custom licence (see repository)Updated today

    git clone https://github.com/datawhalechina/llm-algo-leetcode.git
  19. dstack

    Skills

    A unified orchestration layer for heterogeneous AI compute. It standardizes how to manage compute and run training and inference on GPU clouds, Kubernetes, VMs, or bare-metal clusters.

    Stale GitHub, dstackai 2,293 ★MPL-2.0Updated 18 days ago

    git clone https://github.com/dstackai/dstack.git
  20. PaddleNLP

    AI repositories

    Easy-to-use and powerful LLM and SLM library with awesome model zoo.

    Stale GitHub, PaddlePaddle 13.0k ★Apache-2.0Updated 5 months ago

    git clone https://github.com/PaddlePaddle/PaddleNLP.git
  21. awsome-distributed-ai

    AI repositories

    Best practices, reference architectures, and examples for distributed AI training and inference on AWS.

    Indexed GitHub, awslabs 498 ★MIT-0Updated 2 days ago

    git clone https://github.com/awslabs/awsome-distributed-ai.git
  22. Nemotron-Post-Training-Dataset-v2

    Datasets & benchmarks

    Hugging Face dataset by nvidia

    Stale Hugging Face Hub, nvidia 156 ♥cc-by-4.0Updated 15 months ago 1 note

    nvidia/Nemotron-Post-Training-Dataset-v2
  23. An Agent Skill for Claude Code, Codex and other coding agents: train on rented GPUs without losing checkpoints or paying for idle machines.

    Stale GitHub, Hanyuyuan6 42 ★MITUpdated 25 days ago

    git clone https://github.com/Hanyuyuan6/remote-gpu-trainer.git
  24. doc-adk-training

    Docs & tutorials

    Learn to build, test, and deploy production-ready AI agents with this complete "From Zero to Hero" training course for the Google Agent Development Kit (ADK).

    Indexed GitHub, mauripsale 85 ★Custom licence (see repository)Updated 4 days ago

    git clone https://github.com/mauripsale/doc-adk-training.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.