You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
LoRAX currently only supports text generation models (e.g., causal language models). It lacks support for sequence classification models like AutoModelForSequenceClassification. This issue proposes adding support for AutoModelForSequenceClassification models to LoRAX. This would enable users to serve and perform inference with fine-tuned sequence classification models. This would expand LoRAX's capabilities, allowing users to serve a wider range of models and perform tasks like sentiment analysis, topic classification, and more.
Motivation
Currently, users who want to serve sequence classification models with LoRAX have to rely on external inference APIs or implement their own solutions. This can be cumbersome and less efficient. Adding native support for AutoModelForSequenceClassification would streamline the process and make LoRAX more versatile.
Your contribution
I'm willing to contribute to this feature.
The text was updated successfully, but these errors were encountered:
Feature request
LoRAX currently only supports text generation models (e.g., causal language models). It lacks support for sequence classification models like
AutoModelForSequenceClassification
. This issue proposes adding support forAutoModelForSequenceClassification
models to LoRAX. This would enable users to serve and perform inference with fine-tuned sequence classification models. This would expand LoRAX's capabilities, allowing users to serve a wider range of models and perform tasks like sentiment analysis, topic classification, and more.Motivation
Currently, users who want to serve sequence classification models with LoRAX have to rely on external inference APIs or implement their own solutions. This can be cumbersome and less efficient. Adding native support for
AutoModelForSequenceClassification
would streamline the process and make LoRAX more versatile.Your contribution
I'm willing to contribute to this feature.
The text was updated successfully, but these errors were encountered: