Instructions to use Alt41r/gpt-simpson with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Alt41r/gpt-simpson with Transformers:

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

pipe = pipeline("text-generation", model="Alt41r/gpt-simpson")

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

tokenizer = AutoTokenizer.from_pretrained("Alt41r/gpt-simpson")
model = AutoModelForCausalLM.from_pretrained("Alt41r/gpt-simpson", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Alt41r/gpt-simpson with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Alt41r/gpt-simpson"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alt41r/gpt-simpson",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Alt41r/gpt-simpson

SGLang

How to use Alt41r/gpt-simpson 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 "Alt41r/gpt-simpson" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alt41r/gpt-simpson",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Alt41r/gpt-simpson" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alt41r/gpt-simpson",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Alt41r/gpt-simpson with Docker Model Runner:
```
docker model run hf.co/Alt41r/gpt-simpson
```

gpt-simpson

Commit History

Jun 23, 2023

11:22
Adding `safetensors` variant of this model⁠

SFconvertbot

d33aa2d

Oct 29, 2022

22:44
Update README.md

Alt41r

b731997
22:43
Update README.md

Alt41r

9a1d499
21:59
Update README.md

Alt41r

82acd52
21:58
Update README.md

Alt41r

040559b
21:58
Update README.md

Alt41r

f791087
21:57
Update README.md

Alt41r

acfe44d
21:57
Update README.md

Alt41r

33ae2e1
21:53
Create README.md

Alt41r

0b1f5c9
21:52
Update README.md

Alt41r

e9a3048
21:51
Update README.md

Alt41r

bdbbf89
21:51
Update README.md

Alt41r

5857085
21:49
Create README.md

Alt41r

f9bb0a1
20:58
add tokenizer

Alt41r

15934d0
20:50
add model

Alt41r

d032d2b
20:35
initial commit

Alt41r

d03a1cb

Commit History

Jun 23, 2023

Adding `safetensors` variant of this model⁠

Oct 29, 2022

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Create README.md

Update README.md

Update README.md

Update README.md

Create README.md

add tokenizer

add model

initial commit