• 내용으로 건너뛰기

Out of the Box

사용자 도구

  • 로그인

사이트 도구

  • 최근 바뀜
  • 미디어 관리자
  • 사이트맵
추적: • 2020-12_monte_carlo_transformer_stochastic_self_attention_model_sequence_prediction • offline_reinforcement_learning • bert_pre_training_deep_bidirectional_transformers_language_understanding • docker • train_llm • numexpr • apache • character_controllers_using_motion_vaes • off_dynamics_reinforcement_learning_training_transfer_domain_classifiers • tiny_llm

topic:tiny_llm

문서의 이전 판입니다!


Tiny LLM

  • pico-GPT
    • https://jaykmody.com/blog/gpt-from-scratch/
    • https://github.com/jaymody/picoGPT
    • https://www.dipkumar.dev/becoming-the-unbeatable/posts/gpt-kvcache/
  • minGPT/nanoGPT
    • https://github.com/karpathy/mingpt
    • https://github.com/karpathy/nanoGPT
  • pemtoGPT
    • https://github.com/keyvank/femtoGPT
  • nanoT5
    • https://github.com/PiotrNawrot/nanoT5/tree/main
  • tiny vicuna 1B
    • https://blog.stackademic.com/tiny-vicuna-1b-is-the-lightweight-champion-of-the-tiny-models-f05e459b8018
  • nanoRWKV
    • https://github.com/BlinkDL/nanoRWKV
    • https://github.com/BlinkDL/ChatRWKV/blob/main/RWKV_in_150_lines.py
    • https://github.com/BlinkDL/ChatRWKV/blob/main/RWKV_v5_demo.py
  • T5
    • https://medium.com/mlearning-ai/past-present-perfect-flan-t5-stands-the-test-of-time-e1db93ff7846
  • LaMini
    • https://medium.com/@fabio.matricardi/lamini-power-when-a-small-guy-can-beat-the-giants-b176d0f7558a
  • 2024-01 TinyLlama: An Open-Source Small Language Model
  • 2024-01 StableLM-2-1.6B
  • 2024-01 Monte Carlo Tree Search for Recipe Generation using GPT-2
  • 2023-12 Speeding up the GPT - KV cache
  • 2023-01 GPT in 60 Lines of NumPy
/var/www/html/data/pages/topic/tiny_llm.txt · 마지막으로 수정됨: 2024/03/23 02:42 저자 127.0.0.1

문서 도구

  • 원본 보기
  • 이전 판
  • 역링크
  • Fold/unfold all
  • 맨 위로
별도로 명시하지 않을 경우, 이 위키의 내용은 다음 라이선스에 따라 사용할 수 있습니다: CC Attribution-Noncommercial-Share Alike 4.0 International
CC Attribution-Noncommercial-Share Alike 4.0 International Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki