Instructions to use sambitsingha/mrbully-chatbot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sambitsingha/mrbully-chatbot with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="sambitsingha/mrbully-chatbot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sambitsingha/mrbully-chatbot")
model = AutoModelForCausalLM.from_pretrained("sambitsingha/mrbully-chatbot", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sambitsingha/mrbully-chatbot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sambitsingha/mrbully-chatbot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sambitsingha/mrbully-chatbot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sambitsingha/mrbully-chatbot

SGLang

How to use sambitsingha/mrbully-chatbot with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "sambitsingha/mrbully-chatbot" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sambitsingha/mrbully-chatbot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "sambitsingha/mrbully-chatbot" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sambitsingha/mrbully-chatbot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sambitsingha/mrbully-chatbot with Docker Model Runner:
```
docker model run hf.co/sambitsingha/mrbully-chatbot
```

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

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

Downloads last month: 4

Safetensors

Model size

0.4B params

Tensor type

F32

Model tree for sambitsingha/mrbully-chatbot

Base model

microsoft/DialoGPT-small

Finetuned

(54)

this model