Instructions to use itay1itzhak/T5-Flan-Seed-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use itay1itzhak/T5-Flan-Seed-2 with Transformers:

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

pipe = pipeline("text-generation", model="itay1itzhak/T5-Flan-Seed-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("itay1itzhak/T5-Flan-Seed-2")
model = AutoModelForSeq2SeqLM.from_pretrained("itay1itzhak/T5-Flan-Seed-2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use itay1itzhak/T5-Flan-Seed-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "itay1itzhak/T5-Flan-Seed-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "itay1itzhak/T5-Flan-Seed-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/itay1itzhak/T5-Flan-Seed-2

SGLang

How to use itay1itzhak/T5-Flan-Seed-2 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 "itay1itzhak/T5-Flan-Seed-2" \
    --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": "itay1itzhak/T5-Flan-Seed-2",
		"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 "itay1itzhak/T5-Flan-Seed-2" \
        --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": "itay1itzhak/T5-Flan-Seed-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use itay1itzhak/T5-Flan-Seed-2 with Docker Model Runner:
```
docker model run hf.co/itay1itzhak/T5-Flan-Seed-2
```

Improve model card: license, model type, tags, and links

by nielsr HF Staff - opened Jul 17, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+30

-30

nielsr

Jul 17, 2025

This PR improves the model card for itay1itzhak/T5-Flan by:

Correcting the license from apache-2.0 to mit, aligning with the license stated in the accompanying GitHub repository.
Updating the model type description from "Causal decoder-based transformer" to "Encoder-Decoder transformer", which accurately reflects the T5 architecture.
Removing the causal-lm tag as T5 is an encoder-decoder model, not a causal language model.
Adding a link to the project page (https://itay1itzhak.github.io/planted-in-pretraining) for easier access to related resources.
Updating the sample usage code to correctly use AutoModelForSeq2SeqLM for loading a T5 (encoder-decoder) model, which aligns with the text2text-generation pipeline tag.
Removing the extraneous "File information" section, as it is internal context and not part of the standard model card content.

These changes enhance the model card's accuracy, completeness, and usability for the Hugging Face community.

Improve model card: license, model type, tags, and links288f3790

itay1itzhak changed pull request status to merged Jul 17, 2025

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