knowledge-distillation repositories

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

  1. 1
    kangarooking/cangjie-skill

    把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills(Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skills)

    GitHub · Python · 13,124 stars · 1,557 forks · +103 stars in 24 hours · Trending score 3.79

  2. 2
    titanwings/distilly

    Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill(原同事 Skill).

    GitHub · Python · 26,704 stars · 2,277 forks · +41 stars in 24 hours · Trending score 3.11

  3. 3
    Ampixa/sanoTTS

    sanoTTS (सानो = 'small' in Nepali): 294k–2.27M-parameter neural TTS that runs on a $3 chip, in the browser, or in Python with low-latency streaming.

    GitHub · C · 851 stars · 90 forks · +60 stars in 24 hours · Trending score 3.10

  4. 4
    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

  5. 5
    nick7nlp/Awesome-LLM-On-Policy-Distillation

    A curated collection of papers and resources on On-Policy Distillation for Large Language Models.

    GitHub · Python · 598 stars · 19 forks · +18 stars in 24 hours · Trending score 2.11

  6. 6
    loanhviet/kokoro-vietnamese-distill

    Distilling Kokoro-Vietnamese (82M) into a 9 MB two-voice browser TTS model: recipe, data, frontend and technical report

    GitHub · Python · 28 stars · 13 forks · +1 stars in 24 hours · Trending score 1.24

  7. 7
    JL-GUO/skill-siphon

    吸星大法.skill(Skill-Siphon)是一个面向 Agent Skill 的学习提炼工具:它把优秀 skill 里高手已经写下来的经验,提炼成人能学懂、能练习、能用到自己工作里的资料。实现效果:隔空吸纳、汇入经脉、炼化内力、凝成精华。它通用适配各种支持 Skill 的 Agent 工具,可帮你从高星/热门 skill 或指定 skill 中提炼核心经验,默认生成学习指南、上手实践、来源与边界三类资料。仓库地址:https://github.com/JL-GUO/skill-siphon 路过留下个star再走吧~非常感谢!

    GitHub · 28 stars · 2 forks · +5 stars in 24 hours · Trending score 0.92

  8. 8
    sunwei925/Efficient-FIQA

    🏆 🥇 Winner solution for ICCV VQualA 2025 Face Image Quality Assessment Challenge

    GitHub · Python · 49 stars · 4 forks · +2 stars in 24 hours · Trending score 0.72

  9. 9
    Garfield-kh/TinyAstral

    TinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents

    GitHub · Python · 13 stars · 0 forks · 0 stars in 24 hours · Trending score 0.28

  10. 10
    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 · 89 stars · 7 forks · −12 stars in 24 hours · Trending score 0.26

  11. 11
    peremartra/optipfair

    Structured pruning, knowledge distillation, and fairness analysis for Large Language Models.

    GitHub · Python · 47 stars · 10 forks · 0 stars in 24 hours · Trending score 0.21

  12. 12
    IngTian/witness

    Turns any text stream into a dated history of how its subject changed. Point it at your Claude Code, OpenCode or Codex sessions to track how you think and work, or at market news, research, or any corpus to track how it changed — raw records to observations to bi-temporal facets to narrative, with provenance, served over MCP. Single pure-Go binary.

    GitHub · Go · 12 stars · 2 forks · 0 stars in 24 hours · Trending score 0.09

  13. 13
    ianhequn/26H

    26电赛H满分省一技术方案分享:SZ嵌入式框架、小车架构、K230视觉与完整报告

    GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08

  14. 14
    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

  15. 15
    intel/neural-compressor

    SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

    GitHub · Python · 2,730 stars · 333 forks · 0 stars in 24 hours · Trending score 0.03

  16. 16
    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

  17. 17
    JuneYaooo/lineage-skill

    Distill videos, PDFs, transcripts, and notes into source-backed teacher Agent Skills.

    GitHub · Python · 459 stars · 69 forks · 0 stars in 24 hours · Trending score 0.00

  18. 18
    kissshhot/Awesome-OPD

    A curated paper list on On-Policy Distillation (OPD) & On-Policy Self-Distillation (OPSD) for LLMs — student rollouts + teacher feedback, covering white-box/black-box methods, OPD-RL hybrids, agentic & multimodal applications, and industrial multi-teacher recipes.

    GitHub · Python · 26 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  19. 19
    sanshengai/sansheng-distill

    Claude Code skill: distill a book or video series into one interactive single-file HTML · 书籍/视频深度蒸馏

    GitHub · Python · 57 stars · 7 forks · 0 stars in 24 hours · Trending score 0.00

  20. 20
    codician-team/growmos

    🪐 Growmos: A new approach to agentic AI—a living system expanding its knowledge like the universe, compounding its capabilities, and getting more work done with fewer tokens.

    GitHub · Python · 9 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00

  21. 21
    ayutaz/sanoTTS-jp

    559 K パラメータの日本語 TTS を ESP32-S3 で実時間合成。漢字かな交じり文の形態素解析・アクセント推定まで端末内で走る(M5Stack CoreS3 実機で確認)。推論は依存ゼロの C99、ブラウザ demo あり。arXiv:2608.21378 sanoTTS の日本語 clean-room 再実装。⚠️ コードは MIT ですが、配布モデルの重みは MIT ではありません(LICENSE-MODEL.md。出力に用途制限が伝播します)

    GitHub · Python · 70 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  22. 22
    alphaparkinc/genpark-elastic-weight-consolidation-fisher-reg-skill

    GenPark AI Agent Skill - Elastic Weight Consolidation (EWC) engine calculating Fisher Information Matrix diagonal penalties to prevent catastrophic forgetting during sequential task learning.

    GitHub · Python · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  23. 23
    alphaparkinc/genpark-experience-replay-reservoir-sampling-skill

    GenPark AI Agent Skill - Continual learning experience replay buffer with streaming reservoir sampling and priority weighting to balance past vs new agent trajectories.

    GitHub · Python · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  24. 24
    alphaparkinc/genpark-gradient-episodic-memory-gem-projector-skill

    GenPark AI Agent Skill - Gradient Episodic Memory (GEM / A-GEM) projection engine constraining parameter updates to prevent interference with past task gradients.

    GitHub · Python · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00