Instructions to use research-backup/bart-large-squad-qg-default with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use research-backup/bart-large-squad-qg-default with Transformers:

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

pipe = pipeline("text-generation", model="research-backup/bart-large-squad-qg-default")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("research-backup/bart-large-squad-qg-default")
model = AutoModelForSeq2SeqLM.from_pretrained("research-backup/bart-large-squad-qg-default")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use research-backup/bart-large-squad-qg-default with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/research-backup/bart-large-squad-qg-default

SGLang

How to use research-backup/bart-large-squad-qg-default 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 "research-backup/bart-large-squad-qg-default" \
    --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": "research-backup/bart-large-squad-qg-default",
		"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 "research-backup/bart-large-squad-qg-default" \
        --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": "research-backup/bart-large-squad-qg-default",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use research-backup/bart-large-squad-qg-default with Docker Model Runner:
```
docker model run hf.co/research-backup/bart-large-squad-qg-default
```

asahi417 commited on Sep 3, 2022

Commit

bdb04b5

1 Parent(s): dabb36d

update

Browse files

Files changed (25) hide show

eval/{metric.first.answer.paragraph_answer.question.asahi417_qg_squad.default.json → metric.first.answer.paragraph_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.first.answer.paragraph_sentence.question.asahi417_qg_squad.default.json → metric.first.answer.paragraph_sentence.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.first.answer.sentence_answer.question.asahi417_qg_squad.default.json → metric.first.answer.sentence_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.first.sentence.paragraph_answer.question.asahi417_qg_squad.default.json → metric.first.sentence.paragraph_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.first.sentence.paragraph_sentence.question.asahi417_qg_squad.default.json → metric.first.sentence.paragraph_sentence.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.first.sentence.sentence_answer.question.asahi417_qg_squad.default.json → metric.first.sentence.sentence_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.last.sentence.paragraph_answer.question.asahi417_qg_squad.default.json → metric.last.sentence.paragraph_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.last.sentence.paragraph_sentence.question.asahi417_qg_squad.default.json → metric.last.sentence.paragraph_sentence.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.last.sentence.sentence_answer.question.asahi417_qg_squad.default.json → metric.last.sentence.sentence_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.long.sentence.paragraph_answer.question.asahi417_qg_squad.default.json → metric.long.sentence.paragraph_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.long.sentence.paragraph_sentence.question.asahi417_qg_squad.default.json → metric.long.sentence.paragraph_sentence.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.long.sentence.sentence_answer.question.asahi417_qg_squad.default.json → metric.long.sentence.sentence_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.middle.sentence.paragraph_answer.question.asahi417_qg_squad.default.json → metric.middle.sentence.paragraph_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.middle.sentence.paragraph_sentence.question.asahi417_qg_squad.default.json → metric.middle.sentence.paragraph_sentence.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.middle.sentence.sentence_answer.question.asahi417_qg_squad.default.json → metric.middle.sentence.sentence_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.short.sentence.paragraph_answer.question.asahi417_qg_squad.default.json → metric.short.sentence.paragraph_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.short.sentence.paragraph_sentence.question.asahi417_qg_squad.default.json → metric.short.sentence.paragraph_sentence.question.lmqg_qg_squad.default.json} +0 -0
eval/{metric.short.sentence.sentence_answer.question.asahi417_qg_squad.default.json → metric.short.sentence.sentence_answer.question.lmqg_qg_squad.default.json} +0 -0
eval/{samples.test.hyp.paragraph_answer.question.asahi417_qg_squad.default.txt → samples.test.hyp.paragraph_answer.question.lmqg_qg_squad.default.txt} +0 -0
eval/{samples.test.hyp.paragraph_sentence.question.asahi417_qg_squad.default.txt → samples.test.hyp.paragraph_sentence.question.lmqg_qg_squad.default.txt} +0 -0
eval/{samples.test.hyp.sentence_answer.question.asahi417_qg_squad.default.txt → samples.test.hyp.sentence_answer.question.lmqg_qg_squad.default.txt} +0 -0
eval/{samples.validation.hyp.paragraph_answer.question.asahi417_qg_squad.default.txt → samples.validation.hyp.paragraph_answer.question.lmqg_qg_squad.default.txt} +0 -0
eval/{samples.validation.hyp.paragraph_sentence.question.asahi417_qg_squad.default.txt → samples.validation.hyp.paragraph_sentence.question.lmqg_qg_squad.default.txt} +0 -0
eval/{samples.validation.hyp.sentence_answer.question.asahi417_qg_squad.default.txt → samples.validation.hyp.sentence_answer.question.lmqg_qg_squad.default.txt} +0 -0
trainer_config.json +1 -1

	@@ -1 +1 @@
1	- {"dataset_path": "~~asahi417~~/qg_squad", "dataset_name": "default", "input_types": ["paragraph_answer"], "output_types": ["question"], "prefix_types": null, "model": "facebook/bart-large", "max_length": 512, "max_length_output": 32, "epoch": 10, "batch": 8, "lr": 1.25e-05, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 4, "label_smoothing": 0.1}


1	+ {"dataset_path": "lmqg/qg_squad", "dataset_name": "default", "input_types": ["paragraph_answer"], "output_types": ["question"], "prefix_types": null, "model": "facebook/bart-large", "max_length": 512, "max_length_output": 32, "epoch": 10, "batch": 8, "lr": 1.25e-05, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 4, "label_smoothing": 0.1}