Live data from Hacker News

Viewing profile — dvilasuero

dvilasuero

HN member
Joined
Thu, Aug 05, 2021, 9:30 PM UTC
HN karma
58
Public activity
16 items

About dvilasuero

No profile information was provided.

Recent public activity

  1. comment
    Comment #44837890

    Hey! I'm part of the AI Sheets team. Looking forward to seeing what you think, feedback and ideas are super welcome! We also wrote a blog post with more details:

  2. story
  3. story
    Show HN: Hugging Face Sheets – Excel meets unstructured data and open LLMs

    Hi, I'm one of the developers of Sheets, a new app where we explore new ways to interact with datasets and use AI to brainstorm, research, and create content through tables. It's f…

  4. comment
  5. comment
    Comment #40069512

    Hey! At Argilla, we've been using our previous version of distilabel to build open preference datasets used by 100s of models and top performing models like zephyr-141b. Today we'r…

  6. story
  7. comment
    Comment #38491829

    Model: https://huggingface.co/argilla/notus-7b-v1 Chat UI: https://huggingface.co/spaces/argilla/notus-chat-ui

  8. story
  9. comment
    Comment #38394414

    Hey there! We've just released a new open-source project for AI feedback to build datasets for RLHF-related methods (like DPO). Recent projects like Zephyr and Tulu from AllenAI ha…

  10. story
  11. comment
    Comment #36203245

    I'm Dani, CEO and co-founder of Argilla. Happy to answer any questions you might have and excited to hear your thoughts! More about Argilla GitHub: https://github.com/argilla-io/ar…

  12. comment
    Comment #36201783

    We're very much looking forward to seeing Falcon-40B support on llama.cpp. For production use cases, this is also highly relevant: https://huggingface.co/blog/sagemaker-huggingface…

  13. comment
    Comment #36201624

    Thanks Anakin! we want to bring the data-centric approach to how LLMs are built and fine-tuned too.

  14. comment
    Comment #36200601

    Thanks! The main difference is that Argilla is built as an open-source component to be integrated into the wider MLOps/LLMOps stack. The focus being on continous data collection, m…

  15. story
  16. story