Instructions to use huggingtweets/patrick_exo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huggingtweets/patrick_exo with Transformers:

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

pipe = pipeline("text-generation", model="huggingtweets/patrick_exo")

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

tokenizer = AutoTokenizer.from_pretrained("huggingtweets/patrick_exo")
model = AutoModelForCausalLM.from_pretrained("huggingtweets/patrick_exo", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/patrick_exo with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/patrick_exo

SGLang

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

Docker Model Runner
How to use huggingtweets/patrick_exo with Docker Model Runner:
```
docker model run hf.co/huggingtweets/patrick_exo
```

patrick_exo

Commit History

Jul 7, 2023

04:40
Adding `safetensors` variant of this model⁠

SFconvertbot

80e0eda

May 22, 2021

18:08
upload flax model

patrickvonplaten

b81b0e7
18:08
allow flax

patrickvonplaten

52ac92c

Mar 28, 2021

00:18
Update model preview

boris

e01093d
00:00
Update model preview

boris

8c94950

Mar 27, 2021

23:58
Update model preview

boris

7898415
23:57
New model from https://wandb.ai/wandb/huggingtweets/runs/2weililh

boris

0b57ab4
23:57
initial commit

system HF Staff

aaef533

Commit History

Jul 7, 2023

Adding `safetensors` variant of this model⁠

May 22, 2021

upload flax model

allow flax

Mar 28, 2021

Update model preview

Update model preview

Mar 27, 2021

Update model preview

New model from https://wandb.ai/wandb/huggingtweets/runs/2weililh

initial commit