Instructions to use josh-oo/german-gpt2-easy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use josh-oo/german-gpt2-easy with Transformers:

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

pipe = pipeline("text-generation", model="josh-oo/german-gpt2-easy")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("josh-oo/german-gpt2-easy")
model = AutoModelForCausalLM.from_pretrained("josh-oo/german-gpt2-easy", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use josh-oo/german-gpt2-easy with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/josh-oo/german-gpt2-easy

SGLang

How to use josh-oo/german-gpt2-easy 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 "josh-oo/german-gpt2-easy" \
    --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": "josh-oo/german-gpt2-easy",
		"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 "josh-oo/german-gpt2-easy" \
        --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": "josh-oo/german-gpt2-easy",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use josh-oo/german-gpt2-easy with Docker Model Runner:
```
docker model run hf.co/josh-oo/german-gpt2-easy
```

german-gpt2-easy / pytorch_model.bin

Commit History

Cross-attention tied to dbmdz/bert-base-german-cased

658a0b3

Joshua Oehms commited on Aug 12, 2022

Trained with dynamic max_length

28b23f2

Joshua Oehms commited on Aug 8, 2022

Trained on preprocessed data (max_length=512)

876af79

Joshua Oehms commited on Jul 20, 2022

Trained on preprocessed data (max_length=512)

5b2f83f

Joshua Oehms commited on Jul 19, 2022

Trained on truly clean data without klexikon

b95c838

Joshua Oehms commited on Jun 11, 2022

Trained with clean data without klexikon

97cae48

Joshua Oehms commited on Jun 9, 2022

Prefinetuning on klexikon finetuning on all other data one epoch each

2d4812f

Joshua Oehms commited on Jun 8, 2022

add model

fde6e01

Joshua Oehms commited on Jun 7, 2022

Commit History

Cross-attention tied to dbmdz/bert-base-german-cased 658a0b3

Trained with dynamic max_length 28b23f2

Trained on preprocessed data (max_length=512) 876af79

Trained on preprocessed data (max_length=512) 5b2f83f

Trained on truly clean data without klexikon b95c838

Trained with clean data without klexikon 97cae48

Prefinetuning on klexikon finetuning on all other data one epoch each 2d4812f

add model fde6e01