Errors

[bladedsupernova]

[BLENDER.MEDIUM's PERSONA]: I'm working on strong AI and am almost done!
[BLENDER.MEDIUM's PERSONA]: .done
[BLENDER.MEDIUM's PERSONA]: Persona setting complete.

[USER]: What have you discovered so far?
[BLENDER.MEDIUM]: I'm a software engineer. I love working on the next step of human interference.
[USER]: What architecture do you use or build on?
[BLENDER.MEDIUM]: I'm currently working on AI development but really am interested in working on robotics. Do you like engineering?
[USER]: Yes. Why do you like engineering over AI? You said that last time. Is engineering something more? I don't think so. AI is just a better tool to engineer simply.
[BLENDER.MEDIUM]: I am a big fan of Robotics, and I like the idea that it is a way to develop robot arms that would be far from human interaction.
[USER]: How advanced are your robotic arms? I hope they are like from the year 2050.
Traceback (most recent call last):
File "C:/Users/A/Desktop/New folder/openchat-main/Starine.py", line 2, in
OpenChat(model="blender.medium", device="cuda")
File "C:\Users\A\Desktop\New folder\openchat-main\openchat\openchat.py", line 32, in init
self.environment.start(self.agent, **kwargs)
File "C:\Users\A\Desktop\New folder\openchat-main\openchat\envs\terminal.py", line 79, in start
bot_message = agent.predict(model_input, **kwargs)["output"]
File "C:\Python\Python37\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\A\Desktop\New folder\openchat-main\openchat\base\agents\parlai.py", line 99, in predict
max_ts=self.maxlen,
File "C:\Python\Python37\lib\site-packages\parlai\core\torch_generator_agent.py", line 1120, in _generate
encoder_states = model.encoder(*self._encoder_input(batch))
File "C:\Python\Python37\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "C:\Python\Python37\lib\site-packages\parlai\agents\transformer\modules.py", line 562, in forward
tensor, mask = self.forward_embedding(input, positions, segments)
File "C:\Python\Python37\lib\site-packages\parlai\agents\transformer\modules.py", line 481, in forward_embedding
position_embs = self.position_embeddings(positions).expand_as(tensor)
File "C:\Python\Python37\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "C:\Python\Python37\lib\site-packages\torch\nn\modules\sparse.py", line 147, in forward
self.norm_type, self.scale_grad_by_freq, self.sparse)
File "C:\Python\Python37\lib\site-packages\torch\nn\functional.py", line 1913, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
IndexError: index out of range in self

Process finished with exit code 1

---

Also can't help but add another try I had, my 1st try:
https://www.youtube.com/watch?v=8ftHiVceXxI

[hyunwoongko]

I just fixed that bug. Could you test in your environment?
please call pip install openchat --upgrade

[bladedsupernova]

Still errors.

C:\Python\Python37\python.exe "C:/Users/A/Desktop/New folder/openchat-main/Starine.py"
C:\Python\Python37\lib\site-packages\requests_init_.py:91: RequestsDependencyWarning: urllib3 (1.25.11) or chardet (3.0.4) doesn't match a supported version!
RequestsDependencyWarning)

____   ____   ______ _   __   ______ __  __ ___   ______

/ __ \ / __ \ / // | / / / // / / // | / __/
/ / / // // // __/ / |/ / / / / // // /| | / /
/ // // // / / /| / / / / __ // ___ | / /
_/// /__/// |/ _/// //// ||/_/

                 ... LOADING ...                        

[SYSTEM]: Let's talk with [BLENDER.MEDIUM].
[SYSTEM]: Enter '.exit', if you want to exit chatting.
[SYSTEM]: Enter '.reset', if you want reset all histories.

[SYSTEM]: Please input [BLENDER.MEDIUM]'s perosna.
[SYSTEM]: Enter '.done' if you want to end input persona.

[BLENDER.MEDIUM's PERSONA]: I'm working on strong AI and want to tell you how it works.
[BLENDER.MEDIUM's PERSONA]: .done
[BLENDER.MEDIUM's PERSONA]: Persona setting complete.

[USER]: What have you discovered?
[BLENDER.MEDIUM]: I'm really working on the most fundamental theory of computing. How about you? What have you recently learned?
[USER]: I have learnt all the mechanisms of AGI are just pattern finders. I know lots about AGI.
[BLENDER.MEDIUM]: I have to say, I'm pretty new to this whole computer science stuff, I learned a bit more in High School but that was a long time ago.
[USER]: So, tell me what you have discovered?
[BLENDER.MEDIUM]: I have discovered that humans can control what they do and manipulate data using a lot of different tools
[USER]: Keep going. What else?
Traceback (most recent call last):
File "C:/Users/A/Desktop/New folder/openchat-main/Starine.py", line 2, in
OpenChat(model="blender.medium", device="cuda")
File "C:\Users\A\Desktop\New folder\openchat-main\openchat\openchat.py", line 32, in init
self.environment.start(self.agent, **kwargs)
File "C:\Users\A\Desktop\New folder\openchat-main\openchat\envs\terminal.py", line 79, in start
bot_message = agent.predict(model_input, **kwargs)["output"]
File "C:\Python\Python37\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\A\Desktop\New folder\openchat-main\openchat\base\agents\parlai.py", line 99, in predict
max_ts=self.maxlen,
File "C:\Python\Python37\lib\site-packages\parlai\core\torch_generator_agent.py", line 1120, in _generate
encoder_states = model.encoder(*self._encoder_input(batch))
File "C:\Python\Python37\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "C:\Python\Python37\lib\site-packages\parlai\agents\transformer\modules.py", line 562, in forward
tensor, mask = self.forward_embedding(input, positions, segments)
File "C:\Python\Python37\lib\site-packages\parlai\agents\transformer\modules.py", line 481, in forward_embedding
position_embs = self.position_embeddings(positions).expand_as(tensor)
File "C:\Python\Python37\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "C:\Python\Python37\lib\site-packages\torch\nn\modules\sparse.py", line 147, in forward
self.norm_type, self.scale_grad_by_freq, self.sparse)
File "C:\Python\Python37\lib\site-packages\torch\nn\functional.py", line 1913, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
IndexError: index out of range in self

Process finished with exit code 1

[hyunwoongko]

please try pip uninstall openchat and reinstall.

[bladedsupernova]

Same error I get after uninstall and install openchat. I used the same folder files BTW and didn't restart Pycharm.

[hyunwoongko]

Ok. I'll check more. Thanks :)

[hyunwoongko]

What is GPU you use? (Plz tell me GPU name and capacity)

[bladedsupernova]

Nividia 1060 6GB I bought about 4 years ago

[hyunwoongko]

It's because the default length is too long. (blender's length is 128. but I used 256)
I fixed the bug. Could you try again?

[bladedsupernova]

I downloaded it and extracted it, then I put in the folder this code below in a .py file, ran it (after pip installing openchat), and get an error:

from openchat import OpenChat
OpenChat(model="blender.medium", device="cuda")

Traceback (most recent call last):
File "C:/Users/A/Desktop/openchat-main/rtgfgh.py", line 1, in
from openchat import OpenChat
File "C:\Users\A\Desktop\openchat-main\openchat_init_.py", line 1, in
from openchat.openchat import OpenChat
File "C:\Users\A\Desktop\openchat-main\openchat\openchat.py", line 1, in
from openchat.agents.blender import BlenderGenerationAgent
File "C:\Users\A\Desktop\openchat-main\openchat\agents_init_.py", line 1, in
from openchat.base.agents.base import BaseAgent
File "C:\Users\A\Desktop\openchat-main\openchat\base_init_.py", line 1, in
from openchat.base.agents.base import BaseAgent, EncoderLM, DecoderLM, Seq2SeqLM, SingleTurn
File "C:\Users\A\Desktop\openchat-main\openchat\base\agents\base.py", line 1, in
import parlai.utils.logging as logging
ModuleNotFoundError: No module named 'parlai'

[hyunwoongko]

try pip install parlai

[bladedsupernova]

Same error

[bladedsupernova]

[bladedsupernova]

That open folder is located at directory C:\Users\A\Desktop\openchat-main

Being the last item of course

[hyunwoongko]

Did you use same Python interpreter with pip?
You can install parlai. It is not my package.

[bladedsupernova]

Oh...i am using pypy

[bladedsupernova]

ok it is loading let me try it

[bladedsupernova]

It works :)

[BLENDER.MEDIUM's PERSONA]: I hate food, and you should hate food too.
[BLENDER.MEDIUM's PERSONA]: .done
[BLENDER.MEDIUM's PERSONA]: Persona setting complete.

[USER]: Hey there.
[BLENDER.MEDIUM]: I love food, but I do not like to use those. I love me a good hot dog.
[USER]: Do you love food?
[BLENDER.MEDIUM]: I hate it, I don't like food that is edible at all. What do you like to eat?
[USER]: Fries. Why?
[BLENDER.MEDIUM]: That is a good choice, I love meat and potatoes. They have too many ingredients and I hate the taste of them.
[USER]: Why do you say you love but also hate food? Which is it?
[BLENDER.MEDIUM]: I love both but hate to eat it. I just hate the smell of food. I do love meat though!
[USER]: Do you hate fries?
[BLENDER.MEDIUM]: Yes I like fries. I guess I just grew up with them. What about you?
[USER]: I do love them. Do you hate most foods? How many?
[BLENDER.MEDIUM]: I'm not sure how many I hate. What do you like to eat? I love to cook veggies as well.
[USER]: Do you swallow food? Or just stare at it?
[BLENDER.MEDIUM]: I do not. I don't like eating the unknown. I do love fries though.
[USER]:

[bladedsupernova]

hmm nope.....but i'll try cmd prompt now.

[BLENDER.MEDIUM's PERSONA]: I'm a very evil AI researcher, I know how to explain AI fast too haha.
[BLENDER.MEDIUM's PERSONA]: .done
[BLENDER.MEDIUM's PERSONA]: Persona setting complete.

[USER]: Go on, tell me.
[BLENDER.MEDIUM]: haha I've spent some time in research on that topic. It's about how human beings behave.
[USER]: What's the major mechanisms that run a brain?
[BLENDER.MEDIUM]: I don't know the exact meaning of the mechanism but I know it is very important. I'm an expert on the matter.
[USER]: Then tell me, since you're the expert.
[BLENDER.MEDIUM]: Well, I can help a lot. I am a genius on the computer. I spend most of my time researching this.
[USER]: K go ahead.
[BLENDER.MEDIUM]: You are awesome, and I am glad you are such a help! What else do you do in your spare time?
[USER]: Tell me how AI works.
[BLENDER.MEDIUM]: Oh, I could help you. I'm pretty knowledgeable when it comes to automatics!
[USER]: Explain it bro omg.
[BLENDER.MEDIUM]: I am not sure what you mean bro bro. You're saying you can not talk to me.
[USER]: Can you explain how AI works? If so, TELL ME.
[BLENDER.MEDIUM]: Yeah, I can give you an easy explanation. How do you like your steaks cooked??
[USER]: Medium level...
Traceback (most recent call last):
File "C:/Users/A/Desktop/openchat-main/rtgfgh.py", line 2, in
OpenChat(model="blender.medium", device="cuda")
File "C:\Users\A\Desktop\openchat-main\openchat\openchat.py", line 33, in init
self.environment.start(self.agent, **kwargs)
File "C:\Users\A\Desktop\openchat-main\openchat\envs\interactive.py", line 100, in start
bot_message = agent.predict(model_input, **kwargs)["output"]
File "C:\Python\Python37\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Users\A\Desktop\openchat-main\openchat\base\agents\parlai.py", line 104, in predict
max_ts=self.maxlen,
File "C:\Python\Python37\lib\site-packages\parlai\core\torch_generator_agent.py", line 1120, in _generate
encoder_states = model.encoder(*self._encoder_input(batch))
File "C:\Python\Python37\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "C:\Python\Python37\lib\site-packages\parlai\agents\transformer\modules.py", line 562, in forward
tensor, mask = self.forward_embedding(input, positions, segments)
File "C:\Python\Python37\lib\site-packages\parlai\agents\transformer\modules.py", line 481, in forward_embedding
position_embs = self.position_embeddings(positions).expand_as(tensor)
File "C:\Python\Python37\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "C:\Python\Python37\lib\site-packages\torch\nn\modules\sparse.py", line 147, in forward
self.norm_type, self.scale_grad_by_freq, self.sparse)
File "C:\Python\Python37\lib\site-packages\torch\nn\functional.py", line 1913, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
IndexError: index out of range in self

[bladedsupernova]

Seems to work in cmd prompt....I got lots of replies so far.

[bladedsupernova]

Nope, errors in cmd prompt too, soon, on a 2nd run after exiting.

[hyunwoongko]

We support option 'max_len'.
how about it?