Instructions to use yhavinga/gpt2-large-dutch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yhavinga/gpt2-large-dutch with Transformers:

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

pipe = pipeline("text-generation", model="yhavinga/gpt2-large-dutch")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yhavinga/gpt2-large-dutch")
model = AutoModelForCausalLM.from_pretrained("yhavinga/gpt2-large-dutch", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yhavinga/gpt2-large-dutch with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yhavinga/gpt2-large-dutch

SGLang

How to use yhavinga/gpt2-large-dutch 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 "yhavinga/gpt2-large-dutch" \
    --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": "yhavinga/gpt2-large-dutch",
		"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 "yhavinga/gpt2-large-dutch" \
        --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": "yhavinga/gpt2-large-dutch",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yhavinga/gpt2-large-dutch with Docker Model Runner:
```
docker model run hf.co/yhavinga/gpt2-large-dutch
```

gpt2-large-dutch / commit.sh

yhavinga

Add scripts, model config etc

c6e3db9 over 4 years ago

Raw

History Blame Contribute Delete

500 Bytes

	#!/bin/bash
	source ~/venv/bin/activate

	while true
	do
	echo -n "Checking at .. "
	date
	UPDATED=`git status \| grep flax_model \| grep modified`

	if [ ! -z "$UPDATED" ]
	then
	sleep 120
	FILE=$(find . -name `ls -tR runs \| grep events \| head -n 1` \| tail -n 1)
	STEP=`tensorboard --load_fast=true --inspect --event_file=$FILE \| grep last_step \| awk '{print $2}'`
	git add runs
	git add flax_model.msgpack
	git commit -m "Saving weights and logs step $STEP"
	fi

	sleep 60
	done