Instructions to use lesserfield/gpt2-4chan-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lesserfield/gpt2-4chan-mini with Transformers:

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

pipe = pipeline("text-generation", model="lesserfield/gpt2-4chan-mini")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lesserfield/gpt2-4chan-mini")
model = AutoModelForCausalLM.from_pretrained("lesserfield/gpt2-4chan-mini")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lesserfield/gpt2-4chan-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lesserfield/gpt2-4chan-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lesserfield/gpt2-4chan-mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lesserfield/gpt2-4chan-mini

SGLang

How to use lesserfield/gpt2-4chan-mini 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 "lesserfield/gpt2-4chan-mini" \
    --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": "lesserfield/gpt2-4chan-mini",
		"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 "lesserfield/gpt2-4chan-mini" \
        --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": "lesserfield/gpt2-4chan-mini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lesserfield/gpt2-4chan-mini with Docker Model Runner:
```
docker model run hf.co/lesserfield/gpt2-4chan-mini
```

niizam commited on Apr 20, 2023

Commit

f46f2c3

1 Parent(s): 5fb1b86

minor fix

Browse files

Files changed (8) hide show

gpt2-4chan-mini/config.json → config.json +0 -0
gpt2-4chan-mini/generation_config.json → generation_config.json +0 -0
gpt2-4chan-mini/optimizer.pt → optimizer.pt +0 -0
gpt2-4chan-mini/pytorch_model.bin → pytorch_model.bin +0 -0
gpt2-4chan-mini/rng_state.pth → rng_state.pth +0 -0
gpt2-4chan-mini/scheduler.pt → scheduler.pt +0 -0
gpt2-4chan-mini/trainer_state.json → trainer_state.json +0 -0
gpt2-4chan-mini/training_args.bin → training_args.bin +0 -0

gpt2-4chan-mini/config.json → config.json RENAMED Viewed

File without changes

gpt2-4chan-mini/generation_config.json → generation_config.json RENAMED Viewed

File without changes

gpt2-4chan-mini/optimizer.pt → optimizer.pt RENAMED Viewed

File without changes

gpt2-4chan-mini/pytorch_model.bin → pytorch_model.bin RENAMED Viewed

File without changes

gpt2-4chan-mini/rng_state.pth → rng_state.pth RENAMED Viewed

File without changes

gpt2-4chan-mini/scheduler.pt → scheduler.pt RENAMED Viewed

File without changes

gpt2-4chan-mini/trainer_state.json → trainer_state.json RENAMED Viewed

File without changes

gpt2-4chan-mini/training_args.bin → training_args.bin RENAMED Viewed

File without changes