Instructions to use abertsch/bart-base-govreport with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abertsch/bart-base-govreport with Transformers:

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

pipe = pipeline("text-generation", model="abertsch/bart-base-govreport")

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

tokenizer = AutoTokenizer.from_pretrained("abertsch/bart-base-govreport")
model = AutoModel.from_pretrained("abertsch/bart-base-govreport", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abertsch/bart-base-govreport with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/abertsch/bart-base-govreport

SGLang

How to use abertsch/bart-base-govreport 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 "abertsch/bart-base-govreport" \
    --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": "abertsch/bart-base-govreport",
		"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 "abertsch/bart-base-govreport" \
        --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": "abertsch/bart-base-govreport",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use abertsch/bart-base-govreport with Docker Model Runner:
```
docker model run hf.co/abertsch/bart-base-govreport
```

bart-base-govreport

Commit History

Jul 29, 2023

13:46
Adding `safetensors` variant of this model⁠

SFconvertbot

705de90

Jul 21, 2023

14:32
Upload tokenizer

abertsch

54b38da

May 8, 2023

17:14
Update README.md

abertsch

c8dd98c
17:00
Update README.md

abertsch

ca9640e

May 3, 2023

15:09
Update README.md

abertsch

47b4ea5
14:59
Update README.md

abertsch

1267178
14:58
Create README.md

abertsch

aac433d
14:50
Upload model

abertsch

a24ba8a
14:50
initial commit

abertsch

929a768

Commit History

Jul 29, 2023

Adding `safetensors` variant of this model⁠

Jul 21, 2023

Upload tokenizer

May 8, 2023

Update README.md

Update README.md

May 3, 2023

Update README.md

Update README.md

Create README.md

Upload model

initial commit