Instructions to use readerbench/QAll-Flan-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use readerbench/QAll-Flan-xl with Transformers:

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

pipe = pipeline("text-generation", model="readerbench/QAll-Flan-xl")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("readerbench/QAll-Flan-xl")
model = AutoModelForSeq2SeqLM.from_pretrained("readerbench/QAll-Flan-xl", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use readerbench/QAll-Flan-xl with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/readerbench/QAll-Flan-xl

SGLang

How to use readerbench/QAll-Flan-xl 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 "readerbench/QAll-Flan-xl" \
    --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": "readerbench/QAll-Flan-xl",
		"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 "readerbench/QAll-Flan-xl" \
        --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": "readerbench/QAll-Flan-xl",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use readerbench/QAll-Flan-xl with Docker Model Runner:
```
docker model run hf.co/readerbench/QAll-Flan-xl
```

stefanruseti commited on Apr 19, 2023

Commit

319d0d5

1 Parent(s): a1f5e71

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -8,7 +8,9 @@ model-index:
 pipeline_tag: text2text-generation
 widget:
 - text: "Answer the question based on the context.\nContext: The Review of Politics was founded in 1939 by Gurian, modeled after German Catholic journals. It quickly emerged as part of an international Catholic intellectual revival, offering an alternative vision to positivist philosophy. For 44 years, the Review was edited by Gurian, Matthew Fitzsimons, Frederick Crosson, and Thomas Stritch. Intellectual leaders included Gurian, Jacques Maritain, Frank O'Malley, Leo Richard Ward, F. A. Hermens, and John U. Nef. It became a major forum for political ideas and modern political concerns, especially from a Catholic and scholastic tradition.\nQuestion: Who was the last editor of the Review of Political Science?"
 - text: "Generate a question based on the context and the answer.\nContext: The Review of Politics was founded in 1939 by Gurian, modeled after German Catholic journals. It quickly emerged as part of an international Catholic intellectual revival, offering an alternative vision to positivist philosophy. For 44 years, the Review was edited by Gurian, Matthew Fitzsimons, Frederick Crosson, and Thomas Stritch. Intellectual leaders included Gurian, Jacques Maritain, Frank O'Malley, Leo Richard Ward, F. A. Hermens, and John U. Nef. It became a major forum for political ideas and modern political concerns, especially from a Catholic and scholastic tradition.\nAnswer: Thomas Stritch"
 ---
 <!-- This model card has been generated automatically according to the information Keras had access to. You should

 pipeline_tag: text2text-generation
 widget:
 - text: "Answer the question based on the context.\nContext: The Review of Politics was founded in 1939 by Gurian, modeled after German Catholic journals. It quickly emerged as part of an international Catholic intellectual revival, offering an alternative vision to positivist philosophy. For 44 years, the Review was edited by Gurian, Matthew Fitzsimons, Frederick Crosson, and Thomas Stritch. Intellectual leaders included Gurian, Jacques Maritain, Frank O'Malley, Leo Richard Ward, F. A. Hermens, and John U. Nef. It became a major forum for political ideas and modern political concerns, especially from a Catholic and scholastic tradition.\nQuestion: Who was the last editor of the Review of Political Science?"
+  example_title: Question Answering
 - text: "Generate a question based on the context and the answer.\nContext: The Review of Politics was founded in 1939 by Gurian, modeled after German Catholic journals. It quickly emerged as part of an international Catholic intellectual revival, offering an alternative vision to positivist philosophy. For 44 years, the Review was edited by Gurian, Matthew Fitzsimons, Frederick Crosson, and Thomas Stritch. Intellectual leaders included Gurian, Jacques Maritain, Frank O'Malley, Leo Richard Ward, F. A. Hermens, and John U. Nef. It became a major forum for political ideas and modern political concerns, especially from a Catholic and scholastic tradition.\nAnswer: Thomas Stritch"
+  example_title: Question Generation
 ---
 <!-- This model card has been generated automatically according to the information Keras had access to. You should