|
|
---
|
|
|
language:
|
|
|
- en
|
|
|
license: apache-2.0
|
|
|
base_model: microsoft/DialoGPT-small
|
|
|
tags:
|
|
|
- conversational
|
|
|
- chatbot
|
|
|
- romantic
|
|
|
- supportive
|
|
|
- fine-tuned
|
|
|
library_name: transformers
|
|
|
pipeline_tag: text-generation
|
|
|
---
|
|
|
|
|
|
# Mr.Bully Chatbot 💕
|
|
|
|
|
|
A fine-tuned conversational AI model designed to be supportive, caring, and romantic in conversations.
|
|
|
|
|
|
## Model Description
|
|
|
|
|
|
Mr.Bully is a fine-tuned version of DialoGPT-small, specifically trained to provide supportive and romantic responses in conversations. The model maintains a caring, encouraging personality while engaging users in meaningful dialogue.
|
|
|
|
|
|
## Usage
|
|
|
|
|
|
```python
|
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("sambitsingha/mrbully-chatbot")
|
|
|
model = AutoModelForCausalLM.from_pretrained("sambitsingha/mrbully-chatbot")
|
|
|
|
|
|
# Format your input
|
|
|
prompt = "User: Hello!\nMr.Bully:"
|
|
|
inputs = tokenizer(prompt, return_tensors="pt")
|
|
|
|
|
|
# Generate response
|
|
|
with torch.no_grad():
|
|
|
outputs = model.generate(
|
|
|
inputs.input_ids,
|
|
|
max_length=100,
|
|
|
temperature=0.7,
|
|
|
do_sample=True,
|
|
|
pad_token_id=tokenizer.eos_token_id
|
|
|
)
|
|
|
|
|
|
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
|
|
print(response)
|
|
|
```
|
|
|
|
|
|
## Training
|
|
|
|
|
|
This model was fine-tuned on conversational data with a focus on supportive and romantic dialogue patterns.
|
|
|
|
|
|
## Intended Use
|
|
|
|
|
|
- Personal AI companion
|
|
|
- Supportive conversations
|
|
|
- Romantic chat scenarios
|
|
|
- Mental health support conversations
|
|
|
|
|
|
## Limitations
|
|
|
|
|
|
- May occasionally generate repetitive responses
|
|
|
- Best suited for English conversations
|
|
|
- Requires proper prompt formatting for optimal results
|
|
|
|
|
|
## Model Card Authors
|
|
|
|
|
|
sambitsingha
|
|
|
|
