Instructions to use utpalendu/monk-gpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use utpalendu/monk-gpt with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("utpalendu/monk-gpt")
model = AutoModelForCausalLM.from_pretrained("utpalendu/monk-gpt")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use utpalendu/monk-gpt with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/utpalendu/monk-gpt

SGLang

How to use utpalendu/monk-gpt 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 "utpalendu/monk-gpt" \
    --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": "utpalendu/monk-gpt",
		"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 "utpalendu/monk-gpt" \
        --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": "utpalendu/monk-gpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use utpalendu/monk-gpt with Docker Model Runner:
```
docker model run hf.co/utpalendu/monk-gpt
```

Monk GPT - Philosophical Wisdom Assistant

Model Description

Monk GPT is a fine-tuned GPT-2 model trained on philosophical conversations about life, death, relationships, career, education, and personal growth. The model responds as a wise monk, offering thoughtful, compassionate, and reflective answers to user questions.

Developed by: Utpalendu Barman
Model type: Causal Language Model (GPT-2)
Language: English
Base model: GPT-2
License: MIT

Intended Uses

Direct Use:
This model is designed for philosophical Q&A and reflective conversation. It can be used for:

Personal reflection and journaling
Educational purposes
Conversational AI applications
Meditation and mindfulness tools

Out-of-Scope Use:
The model is not intended for:

Medical, legal, or professional advice
Factual information retrieval
Harmful or manipulative content

Bias, Risks, and Limitations

The model reflects the biases present in its training data and base GPT-2 model
Responses are philosophical and reflective, not factual
May generate unpredictable or inappropriate content
Should be used with human oversight

How to Get Started

from transformers import GPT2Tokenizer, GPT2LMHeadModel

model_name = "utpalendu/monk-gpt"
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
model = GPT2LMHeadModel.from_pretrained(model_name)

def ask_monk(question):
    prompt = f"Q: {question} A:"
    inputs = tokenizer.encode(prompt, return_tensors="pt")
    outputs = model.generate(
        inputs,
        max_length=200,
        temperature=0.8,
        do_sample=True,
        pad_token_id=tokenizer.eos_token_id
    )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response.split("A:")[-1].strip()

print(ask_monk("What is the meaning of life?"))

Downloads last month: 35

Safetensors

Model size

0.1B params

Tensor type

F32

utpalendu
/

monk-gpt

Monk GPT - Philosophical Wisdom Assistant

Model Description

Intended Uses

Bias, Risks, and Limitations

How to Get Started

Space using utpalendu/monk-gpt 1