Instructions to use SicariusSicariiStuff/Question_Builder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SicariusSicariiStuff/Question_Builder with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SicariusSicariiStuff/Question_Builder")
model = AutoModelForCausalLM.from_pretrained("SicariusSicariiStuff/Question_Builder", 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 SicariusSicariiStuff/Question_Builder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SicariusSicariiStuff/Question_Builder

SGLang

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

Docker Model Runner
How to use SicariusSicariiStuff/Question_Builder with Docker Model Runner:
```
docker model run hf.co/SicariusSicariiStuff/Question_Builder
```

Question_Builder

Available in FP16 and GGUF:

FP16
GGUF

Model Details

This model doesn't answer questions🫢! Its goal is to assist the open-source community to easily create new datasets🤗 The best use case is via API, the recommended length of the data is a few short sentences.

The recommended prompt setting is Debug-deterministic with repetition_penalty 1.2:


temperature: 1
top_p: 1
top_k: 1
typical_p: 1
min_p: 1
repetition_penalty: 1.2

Examples:

Citation Information

@llm{Question_Builder,
  author = {SicariusSicariiStuff},
  title = {Question_Builder},
  year = {2024},
  publisher = {Hugging Face},
  url = {https://huggingface.co/SicariusSicariiStuff/Question_Builder}
}