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

Libraries

How to use KennethTM/gpt2-small-danish with Transformers:

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

pipe = pipeline("text-generation", model="KennethTM/gpt2-small-danish")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KennethTM/gpt2-small-danish")
model = AutoModelForCausalLM.from_pretrained("KennethTM/gpt2-small-danish", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KennethTM/gpt2-small-danish with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/KennethTM/gpt2-small-danish

SGLang

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

Docker Model Runner
How to use KennethTM/gpt2-small-danish with Docker Model Runner:
```
docker model run hf.co/KennethTM/gpt2-small-danish
```

KennethTM commited on Jul 11, 2023

Commit

b87a7d4

1 Parent(s): e91704f

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -37,10 +37,13 @@ model = AutoModelForCausalLM.from_pretrained("KennethTM/gpt2-small-danish")
 The model is trained using the Danish part of the [oscar dataset](https://huggingface.co/datasets/oscar) ('unshuffled_deduplicated_da') and a context length of 1024 tokens.
-The model is initialized from the English [GPT-2 small model](https://huggingface.co/gpt2) with new word token embeddings created for Danish using [WECHSEL](https://github.com/CPJKU/wechsel).
 Initially, only the word token embeddings are trained using 50.000 samples. Finally, the whole model is trained using 1.000.000 samples.
 Model training is carried out on an 8 GB GPU.
 # Notes

 The model is trained using the Danish part of the [oscar dataset](https://huggingface.co/datasets/oscar) ('unshuffled_deduplicated_da') and a context length of 1024 tokens.
+The model weights are initialized from the English [GPT-2 small model](https://huggingface.co/gpt2) with new word token embeddings created for Danish using [WECHSEL](https://github.com/CPJKU/wechsel).
 Initially, only the word token embeddings are trained using 50.000 samples. Finally, the whole model is trained using 1.000.000 samples.
+For reference, the model achieves a perplexity of 33.5 on 5.000 random validation samples.
 Model training is carried out on an 8 GB GPU.
 # Notes