Instructions to use MBZUAI/LaMini-Flan-T5-248M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MBZUAI/LaMini-Flan-T5-248M with Transformers:

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

pipe = pipeline("text-generation", model="MBZUAI/LaMini-Flan-T5-248M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("MBZUAI/LaMini-Flan-T5-248M")
model = AutoModelForSeq2SeqLM.from_pretrained("MBZUAI/LaMini-Flan-T5-248M")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MBZUAI/LaMini-Flan-T5-248M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MBZUAI/LaMini-Flan-T5-248M"
# 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-T5-248M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MBZUAI/LaMini-Flan-T5-248M

SGLang

How to use MBZUAI/LaMini-Flan-T5-248M 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-T5-248M" \
    --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-T5-248M",
		"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-T5-248M" \
        --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-T5-248M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MBZUAI/LaMini-Flan-T5-248M with Docker Model Runner:
```
docker model run hf.co/MBZUAI/LaMini-Flan-T5-248M
```

afaji commited on Apr 14, 2023

Commit

c6c73b9

1 Parent(s): 500022f

Training in progress, step 24000

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
training_args.bin +1 -1

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38756b2053f1da048dc2bcf76f85f38e80188a4a8717849365c0bae41dca1b48
 size 990408885

 version https://git-lfs.github.com/spec/v1
+oid sha256:9c1b9426865e4993c2f4296dd6448a42d7044036e6e803bbfab5ad6ed70850e4
 size 990408885

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e26a8e909472455af27dc75ef5afe47f6a68be0a33a1673fee0a5c0c95209784
 size 3771

 version https://git-lfs.github.com/spec/v1
+oid sha256:bd53078681fcdcc813173e7dacaf8ad5a290b2783b1e39331d8e632469f99ffd
 size 3771