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

Libraries

How to use flax-community/gpt2-medium-persian with Transformers:

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

pipe = pipeline("text-generation", model="flax-community/gpt2-medium-persian")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flax-community/gpt2-medium-persian")
model = AutoModelForCausalLM.from_pretrained("flax-community/gpt2-medium-persian")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use flax-community/gpt2-medium-persian with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/flax-community/gpt2-medium-persian

SGLang

How to use flax-community/gpt2-medium-persian 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 "flax-community/gpt2-medium-persian" \
    --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": "flax-community/gpt2-medium-persian",
		"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 "flax-community/gpt2-medium-persian" \
        --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": "flax-community/gpt2-medium-persian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flax-community/gpt2-medium-persian with Docker Model Runner:
```
docker model run hf.co/flax-community/gpt2-medium-persian
```

gpt2-medium-persian / src

Commit History

Add pytorch, tf version

c5a9149

m3hrdadfi commited on Jul 15, 2021

Fix some bugs

d19a8a5

m3hrdadfi commited on Jul 11, 2021

Add log info

3733ce3

m3hrdadfi commited on Jul 11, 2021

Update runner

51b14d7

m3hrdadfi commited on Jul 11, 2021

Add dataset creation script

c92ce97

m3hrdadfi commited on Jul 11, 2021

change run.sh

70704f2

saied commited on Jul 10, 2021

pushing tokenizer

c36ebf7

saied commited on Jul 10, 2021

Add runner, fix some bugs

31bf2aa

m3hrdadfi commited on Jul 9, 2021

Merge remote-tracking branch 'origin/saied' into develop

8918872

m3hrdadfi commited on Jul 9, 2021

Remove junks

a749413

m3hrdadfi commited on Jul 9, 2021

adding remove add and remove tag functions

a32918a

saied commited on Jul 9, 2021

Remove extra file

4350a5a

m3hrdadfi commited on Jul 8, 2021

Add normalization steps, fix som bugs, add tfboard tracker

1809a17

m3hrdadfi commited on Jul 8, 2021

Refine saied code

09f9c26

m3hrdadfi commited on Jul 8, 2021

some modification in preprocessing/urls removing

ad582b6

saied commited on Jul 7, 2021

some modification in preprocessing

79fa2a7

saied commited on Jul 7, 2021

editted data_utils-url,html,streched alphabet

95cd35a

saied commited on Jul 6, 2021

Fix rm files

bce7e0a

m3hrdadfi commited on Jul 5, 2021

Add training script with checkpoint and preprocessing + merge scripts

7cfca48

m3hrdadfi commited on Jul 5, 2021

Merge remote-tracking branch 'origin/hooman' into develop

8812e32

m3hrdadfi commited on Jul 5, 2021

adding dataset prepration module

73d5951

saied commited on Jul 5, 2021

pushing a template clm training script for gpt2

01ae861

Hooman Sedghamiz commited on Jul 3, 2021

Hello gpt2-persian

21d29cb

m3hrdadfi commited on Jul 3, 2021

Commit History

Add pytorch, tf version c5a9149

Fix some bugs d19a8a5

Add log info 3733ce3

Update runner 51b14d7

Add dataset creation script c92ce97

change run.sh 70704f2

pushing tokenizer c36ebf7

Add runner, fix some bugs 31bf2aa

Merge remote-tracking branch 'origin/saied' into develop 8918872

Remove junks a749413

adding remove add and remove tag functions a32918a

Remove extra file 4350a5a

Add normalization steps, fix som bugs, add tfboard tracker 1809a17

Refine saied code 09f9c26

some modification in preprocessing/urls removing ad582b6

some modification in preprocessing 79fa2a7

editted data_utils-url,html,streched alphabet 95cd35a

Fix rm files bce7e0a

Add training script with checkpoint and preprocessing + merge scripts 7cfca48

Merge remote-tracking branch 'origin/hooman' into develop 8812e32

adding dataset prepration module 73d5951

pushing a template clm training script for gpt2 01ae861

Hello gpt2-persian 21d29cb

Add pytorch, tf version

c5a9149

Fix some bugs

d19a8a5

Add log info

3733ce3

Update runner

51b14d7

Add dataset creation script

c92ce97

change run.sh

70704f2

pushing tokenizer

c36ebf7

Add runner, fix some bugs

31bf2aa

Merge remote-tracking branch 'origin/saied' into develop

8918872

Remove junks

a749413

adding remove add and remove tag functions

a32918a

Remove extra file

4350a5a

Add normalization steps, fix som bugs, add tfboard tracker

1809a17

Refine saied code

09f9c26

some modification in preprocessing/urls removing

ad582b6

some modification in preprocessing

79fa2a7

editted data_utils-url,html,streched alphabet

95cd35a

Fix rm files

bce7e0a

Add training script with checkpoint and preprocessing + merge scripts

7cfca48

Merge remote-tracking branch 'origin/hooman' into develop

8812e32

adding dataset prepration module

73d5951

pushing a template clm training script for gpt2

01ae861

Hello gpt2-persian

21d29cb