Instructions to use azugarini/clue-instruct-mpt-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use azugarini/clue-instruct-mpt-7b with Transformers:

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

pipe = pipeline("text-generation", model="azugarini/clue-instruct-mpt-7b", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("azugarini/clue-instruct-mpt-7b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("azugarini/clue-instruct-mpt-7b", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use azugarini/clue-instruct-mpt-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "azugarini/clue-instruct-mpt-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "azugarini/clue-instruct-mpt-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/azugarini/clue-instruct-mpt-7b

SGLang

How to use azugarini/clue-instruct-mpt-7b 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 "azugarini/clue-instruct-mpt-7b" \
    --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": "azugarini/clue-instruct-mpt-7b",
		"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 "azugarini/clue-instruct-mpt-7b" \
        --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": "azugarini/clue-instruct-mpt-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use azugarini/clue-instruct-mpt-7b with Docker Model Runner:
```
docker model run hf.co/azugarini/clue-instruct-mpt-7b
```

Pre-print

More details about the model are available here

Citation

If you find it useful, please cite us:

@inproceedings{zugarini2024clue,
  title={Clue-Instruct: Text-Based Clue Generation for Educational Crossword Puzzles},
  author={Zugarini, Andrea and Zeinalipour, Kamyar and Kadali, Surya Sai and Maggini, Marco and Gori, Marco and Rigutini, Leonardo},
  booktitle={Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  pages={3347--3356},
  year={2024}
}

Downloads last month: 8

Dataset used to train azugarini/clue-instruct-mpt-7b

Collection including azugarini/clue-instruct-mpt-7b

Clue-instruct

Collection

Clue-instruct dataset and different models fine-tuned on it. • 8 items • Updated Nov 8, 2024

Paper for azugarini/clue-instruct-mpt-7b

Clue-Instruct: Text-Based Clue Generation for Educational Crossword Puzzles

Paper • 2404.06186 • Published Apr 9, 2024 • 3