Instructions to use CreatorPhan/ViQA-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CreatorPhan/ViQA-small with Transformers:

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

pipe = pipeline("text-generation", model="CreatorPhan/ViQA-small")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("CreatorPhan/ViQA-small")
model = AutoModelForSeq2SeqLM.from_pretrained("CreatorPhan/ViQA-small", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CreatorPhan/ViQA-small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/CreatorPhan/ViQA-small

SGLang

How to use CreatorPhan/ViQA-small 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 "CreatorPhan/ViQA-small" \
    --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": "CreatorPhan/ViQA-small",
		"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 "CreatorPhan/ViQA-small" \
        --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": "CreatorPhan/ViQA-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CreatorPhan/ViQA-small with Docker Model Runner:
```
docker model run hf.co/CreatorPhan/ViQA-small
```

CreatorPhan commited on Jun 17, 2023

Commit

8263481

1 Parent(s): 70c7ba4

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -1,9 +1,12 @@
 ---
 language:
 - vi
-pipeline_tag: question-answering
 ---

 ---
 language:
 - vi
+pipeline_tag: text2text-generation
 ---
+Mô hình này được tuning từ pretrained ViFlanT5-small model với 77M tham số với 2 epochs trên 87GB text của bộ CC100.
+Mô hình được huấn luyện cho tác vụ đọc hiểu tiếng Việt. Cung cấp cho mô hình câu hỏi và ngữ cảnh (không quá 400 từ) và mô hình sẽ trích xuất ra câu trả lời trong ngữ cảnh đó.