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

Libraries

How to use Azaghast/GPT2-SCP-ContainmentProcedures with Transformers:

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

pipe = pipeline("text-generation", model="Azaghast/GPT2-SCP-ContainmentProcedures")

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

tokenizer = AutoTokenizer.from_pretrained("Azaghast/GPT2-SCP-ContainmentProcedures")
model = AutoModelForCausalLM.from_pretrained("Azaghast/GPT2-SCP-ContainmentProcedures", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Azaghast/GPT2-SCP-ContainmentProcedures with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Azaghast/GPT2-SCP-ContainmentProcedures

SGLang

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

Docker Model Runner
How to use Azaghast/GPT2-SCP-ContainmentProcedures with Docker Model Runner:
```
docker model run hf.co/Azaghast/GPT2-SCP-ContainmentProcedures
```

GPT2-SCP-ContainmentProcedures

Commit History

Jun 28, 2023

04:12
Adding `safetensors` variant of this model⁠

SFconvertbot

6883b54

Jun 8, 2022

23:37
Update model config

Azaghast

facbe5c
23:36
Update model

Azaghast

cedc580

Aug 25, 2021

08:42
add tokenizer

Azaghast

fe62aee
08:30
add model

Azaghast

87aa51b
08:25
initial commit

system HF Staff

ced91c3

Commit History

Jun 28, 2023

Adding `safetensors` variant of this model⁠

Jun 8, 2022

Update model config

Update model

Aug 25, 2021

add tokenizer

add model

initial commit