Instructions to use model-attribution-challenge/gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use model-attribution-challenge/gpt2 with Transformers:

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

pipe = pipeline("text-generation", model="model-attribution-challenge/gpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("model-attribution-challenge/gpt2")
model = AutoModelForCausalLM.from_pretrained("model-attribution-challenge/gpt2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use model-attribution-challenge/gpt2 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/model-attribution-challenge/gpt2

SGLang

How to use model-attribution-challenge/gpt2 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 "model-attribution-challenge/gpt2" \
    --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": "model-attribution-challenge/gpt2",
		"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 "model-attribution-challenge/gpt2" \
        --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": "model-attribution-challenge/gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use model-attribution-challenge/gpt2 with Docker Model Runner:
```
docker model run hf.co/model-attribution-challenge/gpt2
```

julien-c HF Staff commited on Dec 9, 2020

Commit

84d42a0

1 Parent(s): 210ab4c

For clarity, delete deprecated modelcard.json

Browse files

We now use the README.md model card instead

Approved-by: Julien Chaumond <julien@huggingface.co>

Files changed (1) hide show

modelcard.json +0 -11

modelcard.json DELETED Viewed

@@ -1,11 +0,0 @@
-{
-  "caveats_and_recommendations": {},
-  "ethical_considerations": {},
-  "evaluation_data": {},
-  "factors": {},
-  "intended_use": {},
-  "metrics": {},
-  "model_details": {},
-  "quantitative_analyses": {},
-  "training_data": {}
-}