Instructions to use m3hrdadfi/gpt2-persian-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use m3hrdadfi/gpt2-persian-qa with Transformers:

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

pipe = pipeline("text-generation", model="m3hrdadfi/gpt2-persian-qa")

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

tokenizer = AutoTokenizer.from_pretrained("m3hrdadfi/gpt2-persian-qa")
model = AutoModelForCausalLM.from_pretrained("m3hrdadfi/gpt2-persian-qa", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use m3hrdadfi/gpt2-persian-qa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "m3hrdadfi/gpt2-persian-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-persian-qa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/m3hrdadfi/gpt2-persian-qa

SGLang

How to use m3hrdadfi/gpt2-persian-qa 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 "m3hrdadfi/gpt2-persian-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-persian-qa",
		"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 "m3hrdadfi/gpt2-persian-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-persian-qa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use m3hrdadfi/gpt2-persian-qa with Docker Model Runner:
```
docker model run hf.co/m3hrdadfi/gpt2-persian-qa
```

GPT2 QA - Persian

It is a new approach to using GPT2 in other downstream NLP tasks like QA. The model was trained on PersianQA and evaluated on PersianQA and PersiNLU (Reading Comprehension).

Dataset

Evaluation

The following table summarizes the scores obtained by the model.

Dataset	F1 Score (%)	Exact Match (%)	Total (#)
ParsNLU	46.95	20.39	564
PersianQA	45.93	23.19	651

Demo

Streamlit GPT2 QA - Persian

How to use

TODO (will be filled shortly)...

Downloads last month: 27

m3hrdadfi
/

gpt2-persian-qa

GPT2 QA - Persian

Dataset

Evaluation

Demo

How to use

Dataset used to train m3hrdadfi/gpt2-persian-qa

Space using m3hrdadfi/gpt2-persian-qa 1