Instructions to use HiTZ/Medical-mT5-large-multitask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HiTZ/Medical-mT5-large-multitask with Transformers:

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

pipe = pipeline("text-generation", model="HiTZ/Medical-mT5-large-multitask")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("HiTZ/Medical-mT5-large-multitask")
model = AutoModelForSeq2SeqLM.from_pretrained("HiTZ/Medical-mT5-large-multitask", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HiTZ/Medical-mT5-large-multitask with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HiTZ/Medical-mT5-large-multitask"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HiTZ/Medical-mT5-large-multitask",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HiTZ/Medical-mT5-large-multitask

SGLang

How to use HiTZ/Medical-mT5-large-multitask 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 "HiTZ/Medical-mT5-large-multitask" \
    --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": "HiTZ/Medical-mT5-large-multitask",
		"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 "HiTZ/Medical-mT5-large-multitask" \
        --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": "HiTZ/Medical-mT5-large-multitask",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HiTZ/Medical-mT5-large-multitask with Docker Model Runner:
```
docker model run hf.co/HiTZ/Medical-mT5-large-multitask
```

Medical-mT5-large-multitask / tokenizer_config.json

Iker

Upload tokenizer

be5403e verified over 2 years ago

Raw

History Blame Contribute Delete

4.79 kB

	{
	"add_eos_token": true,
	"added_tokens_decoder": {
	"0": {
	"content": "<pad>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "</s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"250100": {
	"content": "<ClinicalEntity>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250101": {
	"content": "<Dis>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250102": {
	"content": "<Premise>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250103": {
	"content": "<Claim>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250104": {
	"content": "<DiseaseNCBI>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250105": {
	"content": "<Disease>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250106": {
	"content": "<Chemical>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250107": {
	"content": "<PROTEINAS>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250108": {
	"content": "<NO_NORMALIZABLES>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250109": {
	"content": "<UNCLEAR>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250110": {
	"content": "<NORMALIZABLES>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250111": {
	"content": "</ClinicalEntity>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250112": {
	"content": "</Dis>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250113": {
	"content": "</Premise>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250114": {
	"content": "</Claim>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250115": {
	"content": "</DiseaseNCBI>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250116": {
	"content": "</Disease>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250117": {
	"content": "</Chemical>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250118": {
	"content": "</PROTEINAS>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250119": {
	"content": "</NO_NORMALIZABLES>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250120": {
	"content": "</UNCLEAR>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"250121": {
	"content": "</NORMALIZABLES>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	}
	},
	"additional_special_tokens": [],
	"clean_up_tokenization_spaces": true,
	"eos_token": "</s>",
	"extra_ids": 0,
	"legacy": true,
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<pad>",
	"sp_model_kwargs": {},
	"tokenizer_class": "T5Tokenizer",
	"unk_token": "<unk>"
	}