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

Libraries

How to use benjamin/gpt2-wechsel-uyghur with Transformers:

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

pipe = pipeline("text-generation", model="benjamin/gpt2-wechsel-uyghur")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("benjamin/gpt2-wechsel-uyghur")
model = AutoModelForCausalLM.from_pretrained("benjamin/gpt2-wechsel-uyghur")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use benjamin/gpt2-wechsel-uyghur with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/benjamin/gpt2-wechsel-uyghur

SGLang

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

Docker Model Runner
How to use benjamin/gpt2-wechsel-uyghur with Docker Model Runner:
```
docker model run hf.co/benjamin/gpt2-wechsel-uyghur
```

gpt2-wechsel-uyghur

Model trained with WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

See the code here: https://github.com/CPJKU/wechsel

And the paper here: https://arxiv.org/abs/2112.06598

Performance

Model	PPL
`gpt2-wechsel-sundanese`	111.72
`gpt2` (retrained from scratch)	149.46

Model	PPL
`gpt2-wechsel-scottish-gaelic`	16.43
`gpt2` (retrained from scratch)	19.53

Model	PPL
`gpt2-wechsel-uyghur`	34.33
`gpt2` (retrained from scratch)	42.82

Model	PPL
`gpt2-wechsel-malagasy`	14.01
`gpt2` (retrained from scratch)	15.93

See our paper for details.

Citation

Please cite WECHSEL as

@misc{minixhofer2021wechsel,
      title={WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models}, 
      author={Benjamin Minixhofer and Fabian Paischer and Navid Rekabsaz},
      year={2021},
      eprint={2112.06598},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Downloads last month: 3

Space using benjamin/gpt2-wechsel-uyghur 1

Paper for benjamin/gpt2-wechsel-uyghur

WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models

Paper • 2112.06598 • Published Dec 13, 2021 • 1