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

Libraries

How to use HScomcom/gpt2-MyLittlePony with Transformers:

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

pipe = pipeline("text-generation", model="HScomcom/gpt2-MyLittlePony")

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

tokenizer = AutoTokenizer.from_pretrained("HScomcom/gpt2-MyLittlePony")
model = AutoModelForCausalLM.from_pretrained("HScomcom/gpt2-MyLittlePony", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HScomcom/gpt2-MyLittlePony with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/HScomcom/gpt2-MyLittlePony

SGLang

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

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

HScomcom commited on Mar 31, 2021

Commit

2d8d23f

1 Parent(s): efa2fe2

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -13,4 +13,4 @@ Demo page: [End point](https://master-gpt2-my-little-pony-fpem123.endpoint.ainiz
     Train runtime: 4943.9641 secs
     Loss: 0.0291
-You can easily GPT-2 fine-tune here later: [teachable-nlp](https://ainize.ai/teachable-nlp)

     Train runtime: 4943.9641 secs
     Loss: 0.0291
+In order to train the GPT-2 model, you write code and require a lot of GPU resources, but you can easily fine-tune here and get APIs later. If you are interested, stop by here.: [teachable-nlp](https://ainize.ai/teachable-nlp)