Closed probicheaux closed 1 week ago
get_model
because we don't know a priori if the PaliGemma model is a LoRA or not. How should I handle that? Put something in the model bucket and check for that? Right now, there's a file adapter_config.json
that exists if and only if the model is a LoRA. Should I use that file to check which class to load in get_model?I have tested this implementation and successfully trained a model with LoRA.
Fine, as long as we resolve this https://github.com/roboflow/inference/pull/464#discussion_r1634304370 we are free to merge, I believe that would only take testing CogVLM and probably setting transformers>=4.41.1
Regarding question 2 form here
get_model(...)
calls internally get_model_type(...)
. Would be best if we could have the information responded from API at that level.
If not feasible, relying on adapter_config.json
is ok, but that probably would take having a single class for LoRA and non-LoRA versions?
@probicheaux - how we plan to move on with this?
@PawelPeczek-Roboflow sorry, I've been super busy. Just fixed the get_model thing by pushing a new model_conversion param that adds peft
to lora models. I also tested cogvlm in the new docker container (verifying transformers==4.41.2
and it works fine.
Description
Add in class that can perform inference using LoRAs
Type of change
Please delete options that are not relevant.
How has this change been tested, please provide a testcase or example of how you tested the change?
Locally
Any specific deployment considerations
n/a
Docs