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

Libraries

How to use ainize/gpt2-spongebob-script-large with Transformers:

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

pipe = pipeline("text-generation", model="ainize/gpt2-spongebob-script-large")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ainize/gpt2-spongebob-script-large")
model = AutoModelForCausalLM.from_pretrained("ainize/gpt2-spongebob-script-large", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ainize/gpt2-spongebob-script-large with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ainize/gpt2-spongebob-script-large

SGLang

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

Docker Model Runner
How to use ainize/gpt2-spongebob-script-large with Docker Model Runner:
```
docker model run hf.co/ainize/gpt2-spongebob-script-large
```

HScomcom commited on May 7, 2021

Commit

2204c14

1 Parent(s): b0c0f37

Create README.md

Browse files

Files changed (1) hide show

README.md +21 -0

README.md ADDED Viewed

	@@ -0,0 +1,21 @@

+### Model information
+    Fine tuning data: https://www.kaggle.com/mikhailgaerlan/spongebob-squarepants-completed-transcripts
+    License: CC-BY-SA
+    Base model: gpt-2 large
+    Epoch: 50
+    Train runtime: 14723.0716 secs
+    Loss: 0.0268
+API page: [Ainize](https://ainize.ai/fpem123/GPT2-Spongebob?branch=master)
+Demo page: [End-point](https://master-gpt2-spongebob-fpem123.endpoint.ainize.ai/)
+### ===Teachable NLP=== ###
+To train a GPT-2 model, write code and require GPU resources, but can easily fine-tune and get an API to use the model here for free.
+Teachable NLP: [Teachable NLP](https://ainize.ai/teachable-nlp)
+Tutorial: [Tutorial](https://forum.ainetwork.ai/t/teachable-nlp-how-to-use-teachable-nlp/65?utm_source=community&utm_medium=huggingface&utm_campaign=model&utm_content=teachable%20nlp)