Instructions to use Masdfasdg/GPT2-Prompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Masdfasdg/GPT2-Prompt with Transformers:

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

pipe = pipeline("text-generation", model="Masdfasdg/GPT2-Prompt")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Masdfasdg/GPT2-Prompt")
model = AutoModelForCausalLM.from_pretrained("Masdfasdg/GPT2-Prompt", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Masdfasdg/GPT2-Prompt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Masdfasdg/GPT2-Prompt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Masdfasdg/GPT2-Prompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Masdfasdg/GPT2-Prompt

SGLang

How to use Masdfasdg/GPT2-Prompt 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 "Masdfasdg/GPT2-Prompt" \
    --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": "Masdfasdg/GPT2-Prompt",
		"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 "Masdfasdg/GPT2-Prompt" \
        --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": "Masdfasdg/GPT2-Prompt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Masdfasdg/GPT2-Prompt with Docker Model Runner:
```
docker model run hf.co/Masdfasdg/GPT2-Prompt
```

Masdfasdg commited on Mar 22, 2021

Commit

ff0c012

1 Parent(s): 01aaf7a

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -2,9 +2,11 @@
 language:
 - en
 tags:
-- gpt-2
 - text-generation
 pipeline_tag: text-generation
 ---
 # GPT-2 Story Generator
@@ -16,7 +18,7 @@ Generate a short story from an input prompt.
 Put the vocab ` [endprompt]` after your input.
 Example of an input:
-```python
 A person with a high school education gets sent back into the 1600s and tries to explain science and technology to the people. [endprompt]
 ```

 language:
 - en
 tags:
+- gpt2
 - text-generation
 pipeline_tag: text-generation
+widget:
+- text: "A person with a high school education gets sent back into the 1600s and tries to explain science and technology to the people. [endprompt]"
 ---
 # GPT-2 Story Generator
 Put the vocab ` [endprompt]` after your input.
 Example of an input:
+```
 A person with a high school education gets sent back into the 1600s and tries to explain science and technology to the people. [endprompt]
 ```