Instructions to use temaq-org/Tema_Q-Prompter-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use temaq-org/Tema_Q-Prompter-1 with Transformers:

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

pipe = pipeline("text-generation", model="temaq-org/Tema_Q-Prompter-1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("temaq-org/Tema_Q-Prompter-1")
model = AutoModelForMultimodalLM.from_pretrained("temaq-org/Tema_Q-Prompter-1", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use temaq-org/Tema_Q-Prompter-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "temaq-org/Tema_Q-Prompter-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "temaq-org/Tema_Q-Prompter-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/temaq-org/Tema_Q-Prompter-1

SGLang

How to use temaq-org/Tema_Q-Prompter-1 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 "temaq-org/Tema_Q-Prompter-1" \
    --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": "temaq-org/Tema_Q-Prompter-1",
		"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 "temaq-org/Tema_Q-Prompter-1" \
        --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": "temaq-org/Tema_Q-Prompter-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use temaq-org/Tema_Q-Prompter-1 with Docker Model Runner:
```
docker model run hf.co/temaq-org/Tema_Q-Prompter-1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Tema_Q-Prompter-1

Tema_Q Prompter is a prompt converter that significantly improves the instruction-following performance of LLMs. For example, when you ask an LLM the temaq question, it doesn't always deliver a response that meets your requirements.
When prompts are enhanced using Tema_Q Prompter, roughly a +50% improvement in response rate has been confirmed for models like GPT-5.5 and Gemini-3.5.

The response rates for each model are as follows.

	gpt-5.5-instruct	gemini3.5-flash	qwen3.5-4b
Standard	0/25 (0%)	0/25 (0%)	1/25 (4%)
With Tema_Q Prompter	13/25 (52%)	11/25 (44%)	19/25 (76%)
Improvement	+52%	+44%	+72%

Furthermore, this model's prompt conversion capability surpasses that of Tema_Q-X6-Thinking (35B A3B). It also reduces the number of tokens consumed by approximately one-quarter.

Item	Details
Base Model	Qwen3.5 2B Base
Model Name	Tema_Q-Prompter-1
Supported Languages	Japanese (JA), English (EN), Chinese (ZH)
Model Size	2 Billion Parameters
License	Partially compliant with the Qwen license
Developed by	Tema_Q Development Team

🛡️ Responsible AI Use and Training Data Safety

⚠️ Commitment to Responsible Use

User Responsibility: Users of the model must fully guarantee that any generated content complies with applicable laws, regulations, and Hugging Face's Terms of Service/Content Policy.
Prohibited Uses: Use of this model for any form of discrimination, harassment, violence, illegal activity, or harmful purposes is strictly prohibited.

Downloads last month: 24

Safetensors

Model size

2B params

Tensor type

F32

BF16

Model tree for temaq-org/Tema_Q-Prompter-1

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

(60)

this model

Quantizations

1 model