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

Libraries

How to use research-backup/bart-large-subjqa-electronics-qg with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

docker model run hf.co/research-backup/bart-large-subjqa-electronics-qg

SGLang

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

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

asahi417 commited on Dec 4, 2022

Commit

e28c375

1 Parent(s): de2c471

model update

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ widget:
 - text: "Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic,  <hl> Cadillac Records <hl> ."
   example_title: "Question Generation Example 3"
 model-index:
-- name: lmqg/bart-large-subjqa-electronics
   results:
   - task:
       name: Text2text Generation
@@ -48,9 +48,9 @@ model-index:
       value: 65.68
 ---
-# Model Card of `lmqg/bart-large-subjqa-electronics`
 This model is fine-tuned version of [lmqg/bart-large-squad](https://huggingface.co/lmqg/bart-large-squad) for question generation task on the [lmqg/qg_subjqa](https://huggingface.co/datasets/lmqg/qg_subjqa) (dataset_name: electronics) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
-This model is continuously fine-tuned with [lmqg/bart-large-squad](https://huggingface.co/lmqg/bart-large-squad).
 ### Overview
 - **Language model:** [lmqg/bart-large-squad](https://huggingface.co/lmqg/bart-large-squad)
@@ -66,7 +66,7 @@ This model is continuously fine-tuned with [lmqg/bart-large-squad](https://huggi
 from lmqg import TransformersQG
 # initialize model
-model = TransformersQG(language="en", model="lmqg/bart-large-subjqa-electronics")
 # model prediction
 questions = model.generate_q(list_context="William Turner was an English painter who specialised in watercolour landscapes", list_answer="William Turner")
@@ -77,7 +77,7 @@ questions = model.generate_q(list_context="William Turner was an English painter
 ```python
 from transformers import pipeline
-pipe = pipeline("text2text-generation", "lmqg/bart-large-subjqa-electronics")
 output = pipe("<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")
 ```
@@ -85,7 +85,7 @@ output = pipe("<hl> Beyonce <hl> further expanded her acting career, starring as
 ## Evaluation
-- ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/bart-large-subjqa-electronics/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_subjqa.electronics.json)
 |            |   Score | Type        | Dataset                                                          |
 |:-----------|--------:|:------------|:-----------------------------------------------------------------|
@@ -119,7 +119,7 @@ The following hyperparameters were used during fine-tuning:
  - gradient_accumulation_steps: 8
  - label_smoothing: 0.15
-The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/bart-large-subjqa-electronics/raw/main/trainer_config.json).
 ## Citation
 ```

 - text: "Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic,  <hl> Cadillac Records <hl> ."
   example_title: "Question Generation Example 3"
 model-index:
+- name: lmqg/bart-large-subjqa-electronics-qg
   results:
   - task:
       name: Text2text Generation
       value: 65.68
 ---
+# Model Card of `lmqg/bart-large-subjqa-electronics-qg`
 This model is fine-tuned version of [lmqg/bart-large-squad](https://huggingface.co/lmqg/bart-large-squad) for question generation task on the [lmqg/qg_subjqa](https://huggingface.co/datasets/lmqg/qg_subjqa) (dataset_name: electronics) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
 ### Overview
 - **Language model:** [lmqg/bart-large-squad](https://huggingface.co/lmqg/bart-large-squad)
 from lmqg import TransformersQG
 # initialize model
+model = TransformersQG(language="en", model="lmqg/bart-large-subjqa-electronics-qg")
 # model prediction
 questions = model.generate_q(list_context="William Turner was an English painter who specialised in watercolour landscapes", list_answer="William Turner")
 ```python
 from transformers import pipeline
+pipe = pipeline("text2text-generation", "lmqg/bart-large-subjqa-electronics-qg")
 output = pipe("<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")
 ```
 ## Evaluation
+- ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/bart-large-subjqa-electronics-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_subjqa.electronics.json)
 |            |   Score | Type        | Dataset                                                          |
 |:-----------|--------:|:------------|:-----------------------------------------------------------------|
  - gradient_accumulation_steps: 8
  - label_smoothing: 0.15
+The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/bart-large-subjqa-electronics-qg/raw/main/trainer_config.json).
 ## Citation
 ```