CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge
Paper • 2109.01653 • Published
How to use fractalego/creak-sense with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="fractalego/creak-sense") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("fractalego/creak-sense")
model = AutoModelForCausalLM.from_pretrained("fractalego/creak-sense")How to use fractalego/creak-sense with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fractalego/creak-sense"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "fractalego/creak-sense",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/fractalego/creak-sense
How to use fractalego/creak-sense with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "fractalego/creak-sense" \
--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": "fractalego/creak-sense",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "fractalego/creak-sense" \
--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": "fractalego/creak-sense",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use fractalego/creak-sense with Docker Model Runner:
docker model run hf.co/fractalego/creak-sense
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This framework is trained on the CREAK dataset.
pip install creak-sense
from creak_sense import CreakSense
sense = CreakSense("fractalego/creak-sense")
claim = "Bananas can be found in a grocery list"
sense.make_sense(claim)
with output "True".
from creak_sense import CreakSense
sense = CreakSense("fractalego/creak-sense")
claim = "Bananas can be found in a grocery list"
sense.get_reason(claim)
with output "Bananas are a staple food".