distillation repositories

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

  1. 1
    AlibabaResearch/SparkDiffusion

    SparkDiffusion: Accelerating DiT video generation by 265× via joint Sparsity, Distillation, Quantization, etc.

    GitHub · Python · 749 stars · 84 forks · +229 stars in 24 hours · Trending score 3.86

  2. 2
    chrisliu298/awesome-on-policy-distillation

    A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models

    GitHub · 926 stars · 43 forks · +60 stars in 24 hours · Trending score 2.93

  3. 3
    yangqi0/petitgpt

    A 124.6M LLM trained from scratch on 13B tokens on a single RTX 4090 — tokenizer, pretraining, post-training, evaluation, and reproducible inference.

    GitHub · Python · 73 stars · 16 forks · +2 stars in 24 hours · Trending score 0.87

  4. 4
    hao-ai-lab/FastVideo

    A unified inference and post-training framework for accelerated video generation.

    GitHub · Python · 4,818 stars · 524 forks · 0 stars in 24 hours · Trending score 0.57

  5. 5
    eatmoreduck/yaya-skills

    Agent Skills 把 X Space 变成中文干货笔记:下载 → 带说话人转写 → LLM 蒸馏 → 分享图 / Turn X Spaces into distilled Chinese notes with speaker labels & share cards.

    GitHub · Python · 10 stars · 1 forks · +1 stars in 24 hours · Trending score 0.55

  6. 6
    Ylsssq926/relic.skill

    万物皆可 Relic — 给灵魂开个 GitHub | Universal Digital Immortality Engine 🧬

    GitHub · Python · 73 stars · 4 forks · +1 stars in 24 hours · Trending score 0.45

  7. 7
    nolabs-ai/deepfabric

    Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline

    GitHub · Python · 897 stars · 84 forks · 0 stars in 24 hours · Trending score 0.32

  8. 8
    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

  9. 9
    shibing624/train-jev

    Train JEV-style System 1 decision models on Qwen3.5 and Qwen3.8-27B: 24-slot decision head, KL distillation, calibration and serving. 在 Qwen 上训练 JEV 风格的 System 1 决策模型。

    GitHub · Python · 21 stars · 2 forks · 0 stars in 24 hours · Trending score 0.14

  10. 10
    mii-llm/palingenesis

    Post-train LLMs and agents from one config: SFT, multi-turn RL in tool environments (MCP, Harbor, OpenEnv), on-policy distillation, DPO and merging, with state-of-the-art defaults.

    GitHub · Python · 7 stars · 2 forks · 0 stars in 24 hours · Trending score 0.10

  11. 11
    ironbee-ai/ironbee-gamer

    Plays browser games live with a fast decision engine: Jev (hosted) or Laya (local). An LLM trains each game's profile from the games it plays, and Laya learns it.

    GitHub · TypeScript · 8 stars · 1 forks · 0 stars in 24 hours · Trending score 0.10

  12. 12
    tterrasson/retrograd

    Run and Fine-tune GGUF models, with LoRA or full weights, from SFT to agentic GRPO

    GitHub · Rust · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.07

  13. 13
    Endgame-Labs/understudy

    A drop-in, CPU-only proxy for System One models (Jev, Rune, Clef). It learns each repeated question from the lead, then answers it itself.

    GitHub · Rust · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.05

  14. 14
    sahilmahendrakar/paradee

    An 8M-parameter English text-to-speech model distilled from Kokoro-82M. 9 MB, runs 18x real time on one CPU thread.

    GitHub · Python · 240 stars · 39 forks · 0 stars in 24 hours · Trending score 0.05

  15. 15
    tomerglick57/Jevstiller

    Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.

    GitHub · Python · 80 stars · 11 forks · 0 stars in 24 hours · Trending score 0.03

  16. 16
    lightly-ai/lightly-train

    All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

    GitHub · Python · 1,728 stars · 121 forks · 0 stars in 24 hours · Trending score 0.00

  17. 17
    songmzhang/KDFlow

    A user-friendly & efficient knowledge distillation framework for LLMs, supporting off-policy, full vocab on-policy (OPD), cross-tokenizer, multimodal, and on-policy self-distillation.

    GitHub · Python · 256 stars · 18 forks · 0 stars in 24 hours · Trending score 0.00

  18. 18
    BioSTEAMDevelopmentGroup/biosteam

    The Biorefinery Simulation and Techno-Economic Analysis Modules

    GitHub · Python · 276 stars · 66 forks · 0 stars in 24 hours · Trending score 0.00

  19. 19
    Lakonik/LakonLab

    Official implementation of AsymFlow, pi-Flow, GMFlow

    GitHub · Python · 477 stars · 27 forks · 0 stars in 24 hours · Trending score 0.00

  20. 20
    rasbt/reasoning-from-scratch

    Implement a reasoning LLM in PyTorch from scratch, step by step

    GitHub · Jupyter Notebook · 5,766 stars · 919 forks · 0 stars in 24 hours · Trending score 0.00

  21. 21
    gyunggyung/AGI-Papers

    A curated archive of breakthroughs in Agents, Architecture, Training, RAG, and On-Device AI.

    GitHub · 426 stars · 59 forks · 0 stars in 24 hours · Trending score 0.00

  22. 22
    NVlabs/FastGen

    NVIDIA FastGen: Fast Generation from Diffusion Models

    GitHub · Python · 1,107 stars · 91 forks · 0 stars in 24 hours · Trending score 0.00

  23. 23
    metaevo-ai/harness-zero

    Harness-Zero: Harness Distillation via Agent-as-Harness

    GitHub · Python · 127 stars · 15 forks · 0 stars in 24 hours · Trending score 0.00

  24. 24
    bladedevoff/stuntd

    Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

    GitHub · Python · 73 stars · 5 forks · 0 stars in 24 hours · Trending score 0.00