Instructions to use abertsch/unlimiformer-bart-booksum-random-encoding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abertsch/unlimiformer-bart-booksum-random-encoding with Transformers:

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

pipe = pipeline("text-generation", model="abertsch/unlimiformer-bart-booksum-random-encoding")

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("abertsch/unlimiformer-bart-booksum-random-encoding")
model = AutoModel.from_pretrained("abertsch/unlimiformer-bart-booksum-random-encoding")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use abertsch/unlimiformer-bart-booksum-random-encoding with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/abertsch/unlimiformer-bart-booksum-random-encoding

SGLang

How to use abertsch/unlimiformer-bart-booksum-random-encoding 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/unlimiformer-bart-booksum-random-encoding" \
    --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/unlimiformer-bart-booksum-random-encoding",
		"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/unlimiformer-bart-booksum-random-encoding" \
        --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/unlimiformer-bart-booksum-random-encoding",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use abertsch/unlimiformer-bart-booksum-random-encoding with Docker Model Runner:
```
docker model run hf.co/abertsch/unlimiformer-bart-booksum-random-encoding
```

abertsch commited on May 8, 2023

Commit

45ffce7

1 Parent(s): abb2814

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -6,6 +6,6 @@ inference: false
 ---
 Model from the preprint [Unlimiformer: Long-Range Transformers with Unlimited Length Input](https://arxiv.org/abs/2305.01625).
-This model was finetuned from a BART-base model using the retrieval-augmented training strategy described in section 3.2 of the paper. It was finetuned on the dataset BookSum (full-book setting).
 *The inference demo is disabled because you must add the Unlimiformer files to your repo before this model can handle unlimited length input!* See the [Unlimiformer GitHub](https://github.com/abertsch72/unlimiformer) for setup instructions.

 ---
 Model from the preprint [Unlimiformer: Long-Range Transformers with Unlimited Length Input](https://arxiv.org/abs/2305.01625).
+This model was finetuned from a BART-base model using the random-encoding training strategy described in section 3.2 of the paper. It was finetuned on the dataset BookSum (full-book setting).
 *The inference demo is disabled because you must add the Unlimiformer files to your repo before this model can handle unlimited length input!* See the [Unlimiformer GitHub](https://github.com/abertsch72/unlimiformer) for setup instructions.