Instructions to use tikeape/Qwen-3-4B-Prompt-Gen-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tikeape/Qwen-3-4B-Prompt-Gen-v1 with Transformers:

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

pipe = pipeline("text-generation", model="tikeape/Qwen-3-4B-Prompt-Gen-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tikeape/Qwen-3-4B-Prompt-Gen-v1")
model = AutoModelForCausalLM.from_pretrained("tikeape/Qwen-3-4B-Prompt-Gen-v1")
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

vLLM

How to use tikeape/Qwen-3-4B-Prompt-Gen-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tikeape/Qwen-3-4B-Prompt-Gen-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tikeape/Qwen-3-4B-Prompt-Gen-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tikeape/Qwen-3-4B-Prompt-Gen-v1

SGLang

How to use tikeape/Qwen-3-4B-Prompt-Gen-v1 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 "tikeape/Qwen-3-4B-Prompt-Gen-v1" \
    --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": "tikeape/Qwen-3-4B-Prompt-Gen-v1",
		"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 "tikeape/Qwen-3-4B-Prompt-Gen-v1" \
        --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": "tikeape/Qwen-3-4B-Prompt-Gen-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use tikeape/Qwen-3-4B-Prompt-Gen-v1 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tikeape/Qwen-3-4B-Prompt-Gen-v1 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tikeape/Qwen-3-4B-Prompt-Gen-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tikeape/Qwen-3-4B-Prompt-Gen-v1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="tikeape/Qwen-3-4B-Prompt-Gen-v1",
    max_seq_length=2048,
)

Docker Model Runner
How to use tikeape/Qwen-3-4B-Prompt-Gen-v1 with Docker Model Runner:
```
docker model run hf.co/tikeape/Qwen-3-4B-Prompt-Gen-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Purpose

The purpose of this model is to generate high quality, realistic prompts that users might actually ask models.

It can generate large amounts of synthetic realistic sounding prompts just by being told "Generate a prompt", or you can request a specific topic.

Issues

The model generates diverse prompts but there a few it directly repeats from the training dataset.
The model is almost 100% english
Although you can just use "Generate a prompt", I highly suggest giving a specific topic as it repeats less.

Status

This is a experiemental version and not the best it can be.

Finetuned with: Unsloth

Downloads last month: 3

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for tikeape/Qwen-3-4B-Prompt-Gen-v1

Quantizations

1 model