GPT2 Telegram Chatbot
1.0.0
Un chatbot de Telegram GPT-2 que ha sido relativamente adaptado para chatear. ¡No dudes en hacerme relaciones públicas y revisaré tu código! El bot no es 100% preciso todo el tiempo (por eso codifiqué una función /retry).
Dado que el robot consume tanta memoria, lo programé en una especie de modo de operación por turnos. Cada entrada restablecerá un temporizador en su ID de cuenta; una vez que el temporizador se agote, el bot quedará libre para que lo utilicen otros usuarios. Se le notificará cuando se acabe el cronómetro y otros usuarios podrán ver cuánto tiempo queda y si el bot está en uso.
Breves instrucciones de instalación en Ubuntu 20/WSL.
Recomiendo encarecidamente mirar jupyter notebook/ipynb en la colaboración de Google.
Instale python3.7 (creo que 3.6 podría funcionar también, pero no 3.8):
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt-get update
sudo apt-get install python3.7
Instale pip en Python 3.7:
wget https://bootstrap.pypa.io/get-pip.py
python3.7 get-pip.py
Instale los requisitos dentro de la carpeta del bot después de clonar el repositorio:
python3.7 -m pip install -r requirements.txt
Nota: En realidad, necesitas 16 GB de RAM o una tarjeta de video de 8 GB. De lo contrario, esperarás para siempre. Puede usar las funciones de GPU con al menos una tarjeta de video de 8 GB que admita cuda takelit 10.0 y cudnn para cuda toolkit 10. Esta instalación también funciona en Windows con Python 3.7 y nvidia, debe ejecutar el símbolo del sistema como administrador ejecutando Python 3.7 en Windows.
Descarga el modelo:
python3.7 download_model.py 1558M
Configure la clave API de su bot de Telegram en src/GPT2-Learning.py
Replace "BOTKEY" with telegram bot token i.e. "1827396499:AAHifc06oS31oQ9L3TuCiZxD9EIfKPi0oWQ"
Ejecute el robot:
Si usa el comando python3:
./start.sh
Si usa el comando python3.7:
python3.7 src/GPT2-Learning.py
Puede editar start.sh para que coincida con su comando de Python como desee.
start - Basic start command.
help - Show quick help command.
chatbot - Chatbot mode, me+you string edit and open-ended questions.
finish - Default finish sentence command counting words as output length.
learnon - Turn on sentence compilation with Me+you string for conversation.
learnoff - Turn off the sentence compilation.
learnreset - Reset the learned conversation.
retry - Retry the current computation.
Aquí hay un ejemplo de cómo aprender el modo chatbot con la última base de datos gpt-2 y top_p configurado en 0,83:
Me: Hello! How are you today? Are you feeling alright? I hope you are doing well and not getting into any trouble.
Bot: Yeah, I'm fine. Do you want to make something to eat?
Me: I already made some food, but thanks! I had some jalapeno poppers. I made a ton of them last night after I sold a lawnmower to some folks I got for free earlier in the day. So what are your plans for the day?
Bot: Nothing special. Nothing exciting in particular. I just wanna chill out for a bit.
Me: Just a typical day of kicking back and relaxing huh? Are you gonna watch cartoons or any movies in particular?
Bot: If it's not sports I'll probably just watch something on the TV.
Me: Sounds alright. I coded on my chatbot project most of the morning. Was waiting on someone to come buy a projector but they haven't shown up yet unfortunately. What do you do for work if you don't mind me asking?
Bot: I'm a web developer and engineer. It's fun.
Me: Cool! I'm also a coder and an ethical hacker. I mostly know how to code in Python but I've been unemployed for some time now after my spine injury. I wish I could have joined the military when I was younger. Were you ever in the military?
Bot: No. I'm not really too proud of my military career. It ended up taking a huge toll on my back.
Me: What happened to your back if you don't mind me asking?
Bot: First of all, it's better than before.
Me: Well that's good to hear. Did you injure your back in the military or doing something else?
Bot: Nope. It's an old injury.
Me: Ah I see- Well I'll talk to you later. Sorry about your back! I hope we can catch up tomorrow!
Bot: Yes, of course. Thanks again for chatting!
INFO:tensorflow:Restoring parameters from models/1558M/model.ckpt
2020-05-10 14:19:43,794 - tensorflow - INFO - Restoring parameters from models/1558M/model.ckpt
==========
Before splitlines: Nothing special. Nothing exciting in particular. I just wanna chill out for a bit. You: I'll try to keep my spirits up. Just keep in mind that today's the 10th anniversary of the citywide strike
==========
==========
Mode: True
Learn: True
Length: 44
==========
Before regex: Nothing special. Nothing exciting in particular. I just wanna chill out for a bit. You: I'll try to keep my spirits up. Just keep in mind that today's the 10th anniversary of the citywide strike
==========
Output: Nothing special. Nothing exciting in particular. I just wanna chill out for a bit.
==========
Raw_text or Original: You: Hello! How are you today? Are you feeling alright? I hope you are doing well and not getting into any trouble. Me: Yeah, I'm fine. Do you want to make something to eat? You: I already made some food, but thanks! I had some jalapeno poppers. I made a ton of them last night after I sold a lawnmower to some folks I got for free earlier in the day. So what are your plans for the day? Me:
==========
Learning text or Next: You: Hello! How are you today? Are you feeling alright? I hope you are doing well and not getting into any trouble. Me: Yeah, I'm fine. Do you want to make something to eat? You: I already made some food, but thanks! I had some jalapeno poppers. I made a ton of them last night after I sold a lawnmower to some folks I got for free earlier in the day. So what are your plans for the day? Me: Nothing special. Nothing exciting in particular. I just wanna chill out for a bit.
==========
top_p out: 0.8338636363636364
==========
top_p in: 0.83
==========
Para obtener una lista de puntuaciones gramaticales, consulte /SCORES.MD.
Consejo:
0.77 top_p puede sonar emotivo, confuso e imitador.
0.66 top_p puede parecer pensado y literal, pero puede tener errores de ascii y de corte.
