Baike.dev
All toolsAI codingTrendingOpen sourceNewsSubmit
Log in
Back to tool

PaLM-rlhf-pytorch · Issues· 20 open

Open on GitHub

Locally synced open issues (discussions stay on GitHub)

  • #69

    あ

    Updated Sep 20, 2025
  • #65

    Edge Case 17

    Updated Jul 27, 2025
  • #35

    Value function

    Updated Jan 17, 2025
  • #61

    Do you need to set `retain_graph=True`?

    Updated Dec 6, 2024
  • #60

    A bug in the implementation of the top-p sampling

    Updated Sep 27, 2024
  • #59

    Is there any documentation to train this on my own data ?

    Updated Feb 28, 2024
  • #58

    How to use lora?

    Updated Feb 16, 2024
  • #57

    Should critic's input be prompt only?

    Updated Nov 27, 2023
  • #23

    ✨ Is possibale to use the ChatGPT of OpenAI to train this ChatGPT?

    Updated Nov 5, 2023
  • #51

    I looked at the llama source code and there is an intermedie layer

    Updated Jun 10, 2023
  • #24

    Is it possible to replace PaLM with other huggingface pretrained language model?

    Updated May 1, 2023
  • #48

    memory-efficient attention is default opened? if i dont use flash attn

    Updated Apr 24, 2023
  • #21

    A few questions on training

    Updated Apr 9, 2023
  • #37

    train your reward model issue

    Updated Mar 19, 2023
  • #22

    The loss function of reward model.

    Updated Feb 12, 2023