Kurt Shuster
Kurt Shuster
are you both able to get other models running on the GPU on your machine via ParlAI?
can you try with just `parlai interactive -mf zoo:blender/blender_3B/model` on 1.6.0 and see if it uses GPU?
hmm yes perhaps try installing as a standard install
with the dev install, it's likely your pytorch cuda did not install correctly
Glad that worked, and thank you for the windows install instructions! I'll go ahead and close this for now but please reopen if there are lingering concerns
Any updates on this PR?
@JackUrb @EricMichaelSmith is there any update here?
As the error states, you'll want to call `self.model.self_observe(response)` after calling `self.model.act()` You can also get around this entirely by simply calling `self.model.respond(input_text)`
Ahh, I may have jumped the gun on your initial message. When you return a scripted dialogue, are you calling `self_observe`? Perhaps you can update `get_response` to call `self_observe` only...
You're saying that, during a live run, and with the lines not commented out, your model runs fine?