Instructions to use MBZUAI/LaMini-Flan-T5-783M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MBZUAI/LaMini-Flan-T5-783M with Transformers:

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

pipe = pipeline("text-generation", model="MBZUAI/LaMini-Flan-T5-783M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("MBZUAI/LaMini-Flan-T5-783M")
model = AutoModelForSeq2SeqLM.from_pretrained("MBZUAI/LaMini-Flan-T5-783M")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MBZUAI/LaMini-Flan-T5-783M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MBZUAI/LaMini-Flan-T5-783M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MBZUAI/LaMini-Flan-T5-783M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MBZUAI/LaMini-Flan-T5-783M

SGLang

How to use MBZUAI/LaMini-Flan-T5-783M 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 "MBZUAI/LaMini-Flan-T5-783M" \
    --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": "MBZUAI/LaMini-Flan-T5-783M",
		"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 "MBZUAI/LaMini-Flan-T5-783M" \
        --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": "MBZUAI/LaMini-Flan-T5-783M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MBZUAI/LaMini-Flan-T5-783M with Docker Model Runner:
```
docker model run hf.co/MBZUAI/LaMini-Flan-T5-783M
```

Limit on Generated Text length

by umesh-c - opened Aug 23, 2023

Discussion

umesh-c

Aug 23, 2023

Hi there,
Is there any official doc which tells whats the supported maximum output length from this model?

I believe FLAN's output length is capped to 512 and BERT's 1024? Is this even correct?

If so, is there any option to increase this limit to generate longer paragraphs using this model?

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