Skip to content
View leonardtang's full-sized avatar

Highlights

  • Pro

Organizations

@haizelabs

Block or report leonardtang

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. haizelabs/llama3-jailbreak haizelabs/llama3-jailbreak Public

    A trivial programmatic Llama 3 jailbreak. Sorry Zuck!

    Python 559 63

  2. haizelabs/dspy-redteam haizelabs/dspy-redteam Public

    Red-Teaming Language Models with DSPy

    Python 207 22

  3. haizelabs/verdict haizelabs/verdict Public

    Inference-time scaling for LLMs-as-a-judge.

    Jupyter Notebook 276 18

  4. haizelabs/j1-micro haizelabs/j1-micro Public

    j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.

    Python 95 6

  5. The-Naughtyformer The-Naughtyformer Public

    The Naughtyformer: A Transformer Understands Offensive Humor (AAAI 2023)

    8 1

  6. LLM-Watermarks LLM-Watermarks Public

    Baselines for Identifying Watermarked Large Language Models (ICML AdvML 2023)

    Python 4 1