Hugging Face's logo

Spaces:
featherless-ai
/
try-this-model
Runtime error

App Files Community
14
try-this-model

Commit History

  1. Change default model to Qwen for now

    DarinVerheijke
    Verified signature
    f47468d

  1. :sparkles: adding meta-llama/Llama-3.3-70B-Instruct

    wxgeorge
    8a4b35c

  1. Update README.md (#12)⁠

    Darok +1: Darok-recursal
    Verified signature
    136dcc2

  2. Update model-cache.json (#11)⁠

    Darok +1: Darok-recursal
    Verified signature
    bfc7d84

  1. Update app.py

    Darok
    Verified signature
    3cf3e67

  2. redirect to featherless models page

    Darok
    Verified signature
    8716d3f

  1. :recycle: take refering url from the gradio environment⁠

    wxgeorge
    a18eddc

  2. :sparkles: updating model list.

    wxgeorge
    ac7e364

  3. :beatle: correct twitter handle.

    wxgeorge
    f1ecb17

  1. :wrench: drop reflection. add Nemotron. make default model.

    wxgeorge
    f02037a

  1. :see_no_evil: hide unused logos.

    wxgeorge
    75d7eaa

  2. :beetle: adding missing logo.

    wxgeorge
    f903097

  1. :pencil: correct twitter handle!

    wxgeorge
    01edef7

  2. :lock: don't accept inference requests for models not on the list⁠

    wxgeorge
    a9b1f7f

  3. :wrench: revert to a different model each day.

    wxgeorge
    674f62d

  4. :see_no_evil: hide unused functions to avoid cluttering api pane.

    wxgeorge
    554cf75

  5. :lipstick: make logo bigger and more prominent, conclude with some calls to action.

    wxgeorge
    fcd14c4

  6. :recycle: refactor larger model whitelisting.

    wxgeorge
    3fa9161

  7. :sparkles: bring back l3.1-8b models.

    wxgeorge
    c7ff178

  8. :wrench: put README content in the right place for easier recreation.

    wxgeorge
    3793467

  9. :sparkles: update model list.

    wxgeorge
    6c352bd

  10. :truck: drop "working" from model cache script name.

    wxgeorge
    ceeab78

  1. annotate qwen 2

    wxgeorge
    306918a

  2. :sparkles: include Qwen2.5-72B

    wxgeorge
    0a89ae4

  1. :goal_net: fail to start if API key is missing.

    wxgeorge
    7f61b1d

  2. :pencil2: updating README

    wxgeorge
    bdde565

  1. :wrench: updating model list

    wxgeorge
    5e8c4b7

  1. :wrench: apply reflection system prompt only to Reflection 70B

    wxgeorge
    bd9ae66

  1. Fix html output

    m8than
    Verified signature
    1ce20f1

  1. :fire: revert manual chat templating for reflection now that it's working in featherless backend.⁠

    wxgeorge
    6f983da

  2. Update app.py

    m8than
    Verified signature
    2433428

  3. Update app.py

    m8than
    Verified signature
    7719c51

  4. Update app.py

    m8than
    Verified signature
    8c568be

  5. Changed the concurrency limit.

    m8than
    Verified signature
    b4b16a1

  6. :pencil2: lead copy tuning

    wxgeorge
    8abfddb

  7. :sparkles: add Reflection-Llama to the annotations.

    wxgeorge
    43df791

  8. :heavy_plus_sign: I really only want transformers but just adding it seems to break HF?

    wxgeorge
    ae83cd8

  9. :poop: cheesy "de"chatformatization of response.

    wxgeorge
    4c36b18

  10. :sparkles: support mattshumer's Reflection

    wxgeorge
    30bad6e

  1. :sparkels: add button to facilitate returning to model card.

    wxgeorge
    68492c3

  2. :lipstick: keep chat interface filling the screen

    wxgeorge
    34e11d5

  3. :chart_with_upwards_trend: associate app attribution with inference request.

    wxgeorge
    77ee232

  1. :sparkles: update model cache constructor to include all models⁠

    wxgeorge
    988b5a0

  2. :rocket: update model list

    wxgeorge
    0810fbd

  1. :wrench: update README to annotate only smaller models.

    wxgeorge
    f3dd871

  2. :wrench: update model listing to avoid unintentionally listing larger models.

    wxgeorge
    2018dd8

  3. :sparkles: make initial model choice change day over day.

    wxgeorge
    a1c24d9

  4. :sparkles: model list update.

    wxgeorge
    7302e17

  1. :sparkles: updating model list.

    wxgeorge
    cc133a4

  1. :wrench: include unhealthy models in model cache as we expect this state to be transient.

    wxgeorge
    8f28494