Redid Enhanced Roleplay AI with Memory and Interactivity

Enhanced Roleplay AI with Memory and Interactivity.msgpack

@@ -0,0 +1,32 @@
+from transformers import pipeline, set_seed
+
+# Initialize the conversation pipeline
+set_seed(42)
+roleplay_bot = pipeline('conversational', model='microsoft/DialoGPT-medium')
+
+# Memory to store past interactions
+memory = []
+
+def update_memory(user_input, bot_response):
+    memory.append({"user": user_input, "bot": bot_response})
+
+def get_memory_context():
+    context = ""
+    for interaction in memory[-5:]:  # limiting memory to last 5 interactions for simplicity
+        context += f"User: {interaction['user']}\nBot: {interaction['bot']}\n"
+    return context
+
+def interact(user_input):
+    context = get_memory_context()
+    input_with_context = context + f"User: {user_input}\n"
+    bot_response = roleplay_bot(input_with_context)[0]['generated_text'].split('\n')[-1]
+    update_memory(user_input, bot_response)
+    return bot_response
+
+# Example interaction
+user_input = "Hi! How are you?"
+print("User:", user_input)
+bot_response = interact(user_input)
+print("Bot:", bot_response)
+
+# Continue with more interactions as needed

README.md

@@ -1,54 +0,0 @@
----
-thumbnail: https://huggingface.co/front/thumbnails/dialogpt.png
-tags:
-- conversational
-license: mit
----
-
-## A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)
-
-DialoGPT is a SOTA large-scale pretrained dialogue response generation model for multiturn conversations. 
-The [human evaluation results](https://github.com/dreasysnail/Dialogpt_dev#human-evaluation) indicate that the response generated from DialoGPT is comparable to human response quality under a single-turn conversation Turing test.
-The model is trained on 147M multi-turn dialogue from Reddit discussion thread. 
-
-* Multi-turn generation examples from an interactive environment:
-
-|Role | Response |
-|---------|--------|
-|User | Does money buy happiness? |
-| Bot |  Depends how much money you spend on it .|
-|User | What is the best way to buy happiness ? |
-| Bot | You just have to be a millionaire by your early 20s, then you can be happy . |
-|User |This is so difficult ! |
-| Bot | You have no idea how hard it is to be a millionaire and happy . There is a reason the rich have a lot of money |
-
-Please find the information about preprocessing, training and full details of the DialoGPT in the [original DialoGPT repository](https://github.com/microsoft/DialoGPT)
-
-ArXiv paper: [https://arxiv.org/abs/1911.00536](https://arxiv.org/abs/1911.00536)
-
-### How to use
-
-Now we are ready to try out how the model works as a chatting partner!
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
-
-
-tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium")
-model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium")
-
-# Let's chat for 5 lines
-for step in range(5):
-	# encode the new user input, add the eos_token and return a tensor in Pytorch
-	new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
-
-	# append the new user input tokens to the chat history
-	bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
-
-	# generated a response while limiting the total chat history to 1000 tokens, 
-	chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
-
-	# pretty print last ouput tokens from bot
-	print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
-```