Code Monkey home page Code Monkey logo

llm_tools's People

Contributors

akjuneja avatar jnehring avatar rainbowrivey avatar

Watchers

 avatar  avatar

Forkers

mhannani

llm_tools's Issues

Memory efficiency

Huggingface reads the whole model into main memory and from there to GPU memory. So for a 27GB model we need 27GB of RAM during startup and afterwards we do not need it.

I remember there is a way to stream the model into the GPU memory instead of above behaviour. We should implement this to safe a large portion of RAM.

Warn about long input text

When the lenght of the input text exceeds a models maximum input length the API should throw an exception.

max_new_tokens parameter crashes the api

curl --location 'http://serv-9205.kl.dfki.de:5000/api/generate?max_new_tokens=10' \
--header 'content-type: application/json' \
--data '{
    "doc": "Title: Immune_system\n\nBackground: Pattern recognition receptors are proteins used by nearly all organisms to identify molecules associated with pathogens. Antimicrobial peptides called defensins are an evolutionarily conserved component of the innate immune response found in all animals and plants, and represent the main form of invertebrate systemic immunity. The complement system and phagocytic cells are also used by most forms of invertebrate life. Ribonucleases and the RNA interference pathway are conserved across all eukaryotes, and are thought to play a role in the immune response to viruses.\n\nQuestion: What pathway that plays a role in immune response to viruses is present in all eukaryotes?\n\nAnswer:"}'

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.