Instructions to use under-tree/choice-question-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use under-tree/choice-question-generator with Transformers:

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

pipe = pipeline("text-generation", model="under-tree/choice-question-generator")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("under-tree/choice-question-generator")
model = AutoModelForCausalLM.from_pretrained("under-tree/choice-question-generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use under-tree/choice-question-generator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "under-tree/choice-question-generator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "under-tree/choice-question-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/under-tree/choice-question-generator

SGLang

How to use under-tree/choice-question-generator 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 "under-tree/choice-question-generator" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "under-tree/choice-question-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "under-tree/choice-question-generator" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "under-tree/choice-question-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use under-tree/choice-question-generator with Docker Model Runner:
```
docker model run hf.co/under-tree/choice-question-generator
```

choice-question-generator

Commit History

Jul 16, 2023

17:18
Adding `safetensors` variant of this model⁠

SFconvertbot

0050db4

Mar 27, 2023

11:16
Training in progress, step 1000

under-tree

4ac290f
11:07
Training in progress, step 500

under-tree

e4cab52

Mar 26, 2023

20:43
End of training

under-tree

5501486
20:35
update model card README.md

under-tree

d723b15
20:28
End of training

under-tree

ebb144e
18:40
End of training

under-tree

cf8aab6
18:37
Training in progress, step 500

under-tree

89e4120
18:33
initial commit

under-tree

f5c636a

Commit History

Jul 16, 2023

Adding `safetensors` variant of this model⁠

Mar 27, 2023

Training in progress, step 1000

Training in progress, step 500

Mar 26, 2023

End of training

update model card README.md

End of training

End of training

Training in progress, step 500

initial commit