Instructions to use philschmid/t5-11b-sharded with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philschmid/t5-11b-sharded with Transformers:

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

pipe = pipeline("text-generation", model="philschmid/t5-11b-sharded")

# Load model directly
from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("philschmid/t5-11b-sharded")
model = AutoModelWithLMHead.from_pretrained("philschmid/t5-11b-sharded")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use philschmid/t5-11b-sharded with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "philschmid/t5-11b-sharded"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "philschmid/t5-11b-sharded",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/philschmid/t5-11b-sharded

SGLang

How to use philschmid/t5-11b-sharded 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 "philschmid/t5-11b-sharded" \
    --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": "philschmid/t5-11b-sharded",
		"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 "philschmid/t5-11b-sharded" \
        --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": "philschmid/t5-11b-sharded",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use philschmid/t5-11b-sharded with Docker Model Runner:
```
docker model run hf.co/philschmid/t5-11b-sharded
```

Fork of t5-11b

This is fork of t5-11b implementing a custom handler.py as an example for how to use t5-11b with inference-endpoints on a single NVIDIA T4.

Model Card for T5 11B - fp16

Use with Inference Endpoints

Hugging Face Inference endpoints can be used with an HTTP client in any language. We will use Python and the requests library to send our requests. (make your you have it installed pip install requests)

Send requests with Pyton

import json
import requests as r

ENDPOINT_URL=""# url of your endpoint
HF_TOKEN=""

# payload samples
regular_payload = { "inputs": "translate English to German: The weather is nice today." }
parameter_payload = {
    "inputs": "translate English to German: Hello my name is Philipp and I am a Technical Leader at Hugging Face",
  "parameters" : {
    "max_length": 40,
  }
}

# HTTP headers for authorization
headers= {
    "Authorization": f"Bearer {HF_TOKEN}",
    "Content-Type": "application/json"
}

# send request
response = r.post(ENDPOINT_URL, headers=headers, json=paramter_payload)
generated_text = response.json()

print(generated_text)

Downloads last month: 12

philschmid
/

t5-11b-sharded

Fork of t5-11b

Model Card for T5 11B - fp16

Use with Inference Endpoints

Send requests with Pyton

Dataset used to train philschmid/t5-11b-sharded