Gianfranco Demarco

@xaiguy i don't think i've conducted that exact experiment, but you can test it if you want!

@sasaadi You can find it here https://github.com/gianfrancodemarco/mm-cot/blob/9e84c2ed2ef6921a56f28911a938b78453496655/src/models/t5_multimodal_generation/model.py#L202

You can also set the parameter eval_acc to a lower value to dump the accumulated results from the GPU to the RAM more often. Obviously, this needs a lot of...

> > You can also set the parameter eval_acc to a lower value to dump the accumulated results from the GPU to the RAM more often. Obviously, this needs a...

Bump

I drafted a simple implementation with pygraphviz which gets something like this: 

@Nazareka i've opened #71. Let me know if it works for you or if you have any suggestion

@zachschillaci27 i've migrated my code to _pyvis_ and it seems to work, however it would require some parameters fine-tuning to have a nice spread out visualization. If you want to...

@hinthornw I've used the implementation from the latest version of LangChain, but i get this, which is not what I was expecting: 

Bump!