Instructions to use AlanRobotics/ruT5_q_a with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlanRobotics/ruT5_q_a with Transformers:

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

pipe = pipeline("text-generation", model="AlanRobotics/ruT5_q_a")

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

tokenizer = AutoTokenizer.from_pretrained("AlanRobotics/ruT5_q_a")
model = AutoModelForSeq2SeqLM.from_pretrained("AlanRobotics/ruT5_q_a", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AlanRobotics/ruT5_q_a with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlanRobotics/ruT5_q_a"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlanRobotics/ruT5_q_a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AlanRobotics/ruT5_q_a

SGLang

How to use AlanRobotics/ruT5_q_a 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 "AlanRobotics/ruT5_q_a" \
    --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": "AlanRobotics/ruT5_q_a",
		"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 "AlanRobotics/ruT5_q_a" \
        --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": "AlanRobotics/ruT5_q_a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AlanRobotics/ruT5_q_a with Docker Model Runner:
```
docker model run hf.co/AlanRobotics/ruT5_q_a
```

ruT5_q_a

Commit History

Jul 5, 2023

13:02
Adding `safetensors` variant of this model⁠

SFconvertbot

0a1bbd5

Apr 27, 2023

15:18
Create README.md

AlanRobotics

6a04d5f
15:16
Rename README.md to readme

AlanRobotics

1ffed76
15:12
Update README.md

AlanRobotics

f8507f2
15:03
Update README.md

AlanRobotics

d304e2c
15:02
Create README.md

AlanRobotics

86696bd
14:49
Upload tokenizer

AlanRobotics

144eeb1
14:45
Upload tokenizer

AlanRobotics

7b7af6b

Apr 18, 2023

08:16
Upload T5ForConditionalGeneration

AlanRobotics

2f02eef
06:56
initial commit

AlanRobotics

65bdcad

Commit History

Jul 5, 2023

Adding `safetensors` variant of this model⁠

Apr 27, 2023

Create README.md

Rename README.md to readme

Update README.md

Update README.md

Create README.md

Upload tokenizer

Upload tokenizer

Apr 18, 2023

Upload T5ForConditionalGeneration

initial commit