|
--- |
|
language: |
|
- en |
|
tags: |
|
- conversational |
|
co2_eq_emissions: |
|
emissions: "940" |
|
source: "mlco2.github.io" |
|
training_type: "fine-tuning" |
|
geographical_location: "West Java, Indonesia" |
|
hardware_used: "1 Tesla P100" |
|
license: cc-by-nc-sa-4.0 |
|
widget: |
|
- text: "Hey kekbot! What's up?" |
|
example_title: "Asking what's up" |
|
- text: "Hey kekbot! How r u?" |
|
example_title: "Asking how he is" |
|
--- |
|
> THIS MODEL IS IN PUBLIC BETA, PLEASE DO NOT EXPECT ANY FORM OF STABILITY IN ITS CURRENT STATE. |
|
# Art Union server chatbot |
|
|
|
Based on a DialoGPT-medium model, fine-tuned to a small subset (115k<= messages) of Art Union's general-chat channel. |
|
|
|
### Current issues |
|
(Which hopefully will be fixed in future iterations) Include, but not limited to: |
|
- Limited turns, after ~11 turns output may break for no apparent reason. |
|
- Inconsistent variance, acts like an overfitted model from time to time for no reason whatsoever. |
|
|
