DialoGPT-small-Rick/README.md

language, license, tags, base_model, pipeline_tag

language	license	tags	base_model	pipeline_tag
en	mit	text-generation conversational dialogpt rick-and-morty fine-tuned pytorch transformers	microsoft/DialoGPT-small	text-generation

DialoGPT-small-Rick 🧪

A conversational AI fine-tuned to talk like Rick Sanchez from Rick and Morty. Built on top of microsoft/DialoGPT-small and trained on Rick's dialogue from the show.

---

🚀 Try it Live

👉 RickChatBot — Gradio Space

---

🧠 Model Details

Property	Value
Base Model	microsoft/DialoGPT-small
Architecture	GPT-2 (117M parameters)
Task	Conversational Text Generation
Fine-tuned on	Rick Sanchez dialogue (Rick & Morty)
Framework	PyTorch + HuggingFace Transformers
Language	English

---

💬 How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("iamhariraj/DialoGPT-small-Rick")
model = AutoModelForCausalLM.from_pretrained("iamhariraj/DialoGPT-small-Rick")

chat_history_ids = None

print("Talk to Rick (type 'quit' to exit)")
while True:
    user_input = input("You: ")
    if user_input.lower() == "quit":
        break

    input_ids = tokenizer.encode(
        user_input + tokenizer.eos_token,
        return_tensors="pt"
    )

    if chat_history_ids is not None:
        input_ids = torch.cat([chat_history_ids, input_ids], dim=-1)

    chat_history_ids = model.generate(
        input_ids,
        max_length=1000,
        pad_token_id=tokenizer.eos_token_id,
        no_repeat_ngram_size=3,
        do_sample=True,
        top_k=100,
        top_p=0.7,
        temperature=0.8
    )

    response = tokenizer.decode(
        chat_history_ids[:, input_ids.shape[-1]:][0],
        skip_special_tokens=True
    )
    print(f"Rick: {response}")

---

🎯 Example Conversations

You	Rick
"What is the meaning of life?"	(Rick-style nihilistic response)
"Can you build me a portal gun?"	(Rick flexing his genius)
"I need your help"	(sarcastic Rick response)

---

⚠️ Limitations

• Based on DialoGPT-small — responses can sometimes be generic or repetitive
• May not always stay perfectly in character
• Not suitable for serious or sensitive conversations
• Trained on a limited dialogue dataset

---

🔧 Training

• Base: microsoft/DialoGPT-small
• Data: Rick Sanchez lines extracted from Rick and Morty scripts
• Framework: HuggingFace Transformers + PyTorch
• Trainer: HuggingFace Trainer API

---

👤 Author

Made by iamhariraj

---

📄 License

MIT