rajpurkar/squad
Viewer • Updated • 98.2k • 146k • 363
How to use m3hrdadfi/gpt2-QA with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="m3hrdadfi/gpt2-QA") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("m3hrdadfi/gpt2-QA")
model = AutoModelForCausalLM.from_pretrained("m3hrdadfi/gpt2-QA")How to use m3hrdadfi/gpt2-QA with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "m3hrdadfi/gpt2-QA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "m3hrdadfi/gpt2-QA",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/m3hrdadfi/gpt2-QA
How to use m3hrdadfi/gpt2-QA with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "m3hrdadfi/gpt2-QA" \
--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": "m3hrdadfi/gpt2-QA",
"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 "m3hrdadfi/gpt2-QA" \
--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": "m3hrdadfi/gpt2-QA",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use m3hrdadfi/gpt2-QA with Docker Model Runner:
docker model run hf.co/m3hrdadfi/gpt2-QA
Using GPT2 in other downstream NLP tasks like QA. The model was trained and evaluated on squad.
The following table summarizes the scores obtained by the model.
TODO (will be filled shortly)...