Instructions to use lmqg/mt5-base-zhquad-qag with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmqg/mt5-base-zhquad-qag with Transformers:

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

pipe = pipeline("text-generation", model="lmqg/mt5-base-zhquad-qag")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("lmqg/mt5-base-zhquad-qag")
model = AutoModelForSeq2SeqLM.from_pretrained("lmqg/mt5-base-zhquad-qag", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lmqg/mt5-base-zhquad-qag with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmqg/mt5-base-zhquad-qag"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmqg/mt5-base-zhquad-qag",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lmqg/mt5-base-zhquad-qag

SGLang

How to use lmqg/mt5-base-zhquad-qag 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 "lmqg/mt5-base-zhquad-qag" \
    --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": "lmqg/mt5-base-zhquad-qag",
		"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 "lmqg/mt5-base-zhquad-qag" \
        --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": "lmqg/mt5-base-zhquad-qag",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lmqg/mt5-base-zhquad-qag with Docker Model Runner:
```
docker model run hf.co/lmqg/mt5-base-zhquad-qag
```

Generating bad result even for the example.

by LetsJumP - opened Jan 15, 2024

Discussion

LetsJumP

Jan 15, 2024

南安普敦的警察服务由汉普郡警察提供。南安普敦行动的主要基地是一座新的八层专用建筑，造价3000万英镑。该建筑位于南路，2011年启用，靠近南安普敦中央火车站。此前，南安普顿市中心的行动位于市民中心西翼，但由于设施老化，加上计划在旧警察局和地方法院建造一座新博物馆，因此必须搬迁。在Portswood、Banister Park、Hille和Shirley还有其他警察局，在南安普顿中央火车站还有一个英国交通警察局。

question: 南安普敦的警察局和南安普敦的警察局?

asahi417

LMQG org Jan 18, 2024

Hi, thanks for the feedback! I'll check the model in detail and plan an update on the model when I have time.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment