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

Libraries

How to use HooshvareLab/gpt2-fa with Transformers:

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

pipe = pipeline("text-generation", model="HooshvareLab/gpt2-fa")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HooshvareLab/gpt2-fa")
model = AutoModelForCausalLM.from_pretrained("HooshvareLab/gpt2-fa", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HooshvareLab/gpt2-fa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HooshvareLab/gpt2-fa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HooshvareLab/gpt2-fa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HooshvareLab/gpt2-fa

SGLang

How to use HooshvareLab/gpt2-fa 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 "HooshvareLab/gpt2-fa" \
    --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": "HooshvareLab/gpt2-fa",
		"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 "HooshvareLab/gpt2-fa" \
        --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": "HooshvareLab/gpt2-fa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HooshvareLab/gpt2-fa with Docker Model Runner:
```
docker model run hf.co/HooshvareLab/gpt2-fa
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

ParsGPT2

BibTeX entry and citation info

Please cite in publications as the following:

@misc{ParsGPT2,
  author = {Hooshvare Team},
  title = {ParsGPT2 the Persian version of GPT2},
  year = {2021},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/hooshvare/parsgpt}},
}

Questions?

Post a Github issue on the ParsGPT2 Issues repo.

Downloads last month: 1,861

Model tree for HooshvareLab/gpt2-fa

Adapters

1 model

Finetunes

5 models

Quantizations

1 model

HooshvareLab
/

gpt2-fa

ParsGPT2

BibTeX entry and citation info

Questions?

Model tree for HooshvareLab/gpt2-fa

Spaces using HooshvareLab/gpt2-fa 31