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

Libraries

How to use huggingtweets/onboardmass with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/onboardmass with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/onboardmass

SGLang

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

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

onboardmass

Commit History

May 22, 2021

17:28
upload flax model

patrickvonplaten

39bbe25
17:27
allow flax

patrickvonplaten

45fa4e8

Oct 9, 2020

21:42
Update README.md

system HF Staff

e0a43bd
21:41
Update README.md

system HF Staff

e02a2b1
21:40
Update merges.txt

system HF Staff

68d9fad
21:40
Update vocab.json

system HF Staff

fa9ffd2
21:40
Update config.json

system HF Staff

50c5d67
21:40
Update special_tokens_map.json

system HF Staff

5ca1f42
21:40
Update tokenizer_config.json

system HF Staff

d68fad0
21:40
Update README.md

system HF Staff

bb56af9
21:40
Update pytorch_model.bin

system HF Staff

3d3b65e
18:12
Update README.md

system HF Staff

77f47ff
18:08
Update merges.txt

system HF Staff

2b2523c
18:08
Update vocab.json

system HF Staff

d3fa4de
18:08
Update config.json

system HF Staff

02af227
18:08
Update special_tokens_map.json

system HF Staff

8e48e66
18:08
Update tokenizer_config.json

system HF Staff

efb4707
18:08
Update README.md

system HF Staff

0d1489f
18:08
initial commit

system HF Staff

59d1ecf

Commit History

May 22, 2021

upload flax model

allow flax

Oct 9, 2020

Update README.md

Update README.md

Update merges.txt

Update vocab.json

Update config.json

Update special_tokens_map.json

Update tokenizer_config.json

Update README.md

Update pytorch_model.bin

Update README.md

Update merges.txt

Update vocab.json

Update config.json

Update special_tokens_map.json

Update tokenizer_config.json

Update README.md

initial commit