Instructions to use cenkersisman/gpt2-turkish-128-token with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cenkersisman/gpt2-turkish-128-token with Transformers:

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

pipe = pipeline("text-generation", model="cenkersisman/gpt2-turkish-128-token")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cenkersisman/gpt2-turkish-128-token")
model = AutoModelForCausalLM.from_pretrained("cenkersisman/gpt2-turkish-128-token", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cenkersisman/gpt2-turkish-128-token with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cenkersisman/gpt2-turkish-128-token"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cenkersisman/gpt2-turkish-128-token",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cenkersisman/gpt2-turkish-128-token

SGLang

How to use cenkersisman/gpt2-turkish-128-token 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 "cenkersisman/gpt2-turkish-128-token" \
    --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": "cenkersisman/gpt2-turkish-128-token",
		"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 "cenkersisman/gpt2-turkish-128-token" \
        --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": "cenkersisman/gpt2-turkish-128-token",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cenkersisman/gpt2-turkish-128-token with Docker Model Runner:
```
docker model run hf.co/cenkersisman/gpt2-turkish-128-token
```

🚩 Report: Copyright infringement

by ozgengoknar - opened Apr 11

Discussion

ozgengoknar

Apr 11

Infringement of copyright of Gorkem Goknar TurkishGPTmodel.Commitment date s can be compared .Citation is needed.Thıs person uses Görkem Göknar's base models as if he owns and irequires citation.

no-mad

HF Staff Apr 14

Hi @cenkersisman
Would you mind chiming in here?

@ozgengoknar Thank you for reporting, if you are not able to come to a resolution here, could you please forward us a DMCA takedown notice so we can help you move this along?

cenkersisman

Owner 23 days ago

Hi @ozgengoknar and @no-mad ,

Once again, this claim is completely false.

If you look at the config.json file for this repository, the _name_or_path is explicitly set to "C:\PROJECTS\PYTHON\chatbotgpt-turkish-128\output_model_dir\checkpoint-7618500". This clearly demonstrates that this model was trained locally from scratch on my own Windows machine up to over 7.6 million steps. It has absolutely zero connection to Görkem Göknar's base models.

It appears the complainant is simply copy-pasting the same baseless copyright claim across all my Turkish GPT-2 models without checking the actual repository files. I request that HF staff review the technical evidence in my config.json files and close all these invalid claims immediately.

no-mad

HF Staff 23 days ago

Hi @cenkersisman

Thanks a million for clarifying 🙏

Closing this report as we did not receive a valid takedown notice

no-mad HF Staff changed discussion status to closed 23 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment