Text Generation
Transformers
PyTorch
Safetensors
mt5
text2text-generation
medical
multilingual
medic
Instructions to use HiTZ/Medical-mT5-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HiTZ/Medical-mT5-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HiTZ/Medical-mT5-large")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("HiTZ/Medical-mT5-large") model = AutoModelForSeq2SeqLM.from_pretrained("HiTZ/Medical-mT5-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use HiTZ/Medical-mT5-large 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" # 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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/HiTZ/Medical-mT5-large
- SGLang
How to use HiTZ/Medical-mT5-large 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" \ --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", "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" \ --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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use HiTZ/Medical-mT5-large with Docker Model Runner:
docker model run hf.co/HiTZ/Medical-mT5-large
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,7 @@ tags:
|
|
| 18 |
- medic
|
| 19 |
datasets:
|
| 20 |
- HiTZ/Multilingual-Medical-Corpus
|
|
|
|
| 21 |
---
|
| 22 |
|
| 23 |
<p align="center">
|
|
@@ -131,7 +132,7 @@ tokenizer = AutoTokenizer.from_pretrained("HiTZ/Medical-mT5-large")
|
|
| 131 |
model = AutoModelForSeq2SeqLM.from_pretrained("HiTZ/Medical-mT5-large")
|
| 132 |
```
|
| 133 |
|
| 134 |
-
The model has been trained using the T5 masked language
|
| 135 |
|
| 136 |
<p align="center">
|
| 137 |
<br>
|
|
|
|
| 18 |
- medic
|
| 19 |
datasets:
|
| 20 |
- HiTZ/Multilingual-Medical-Corpus
|
| 21 |
+
base_model: google/mt5-large
|
| 22 |
---
|
| 23 |
|
| 24 |
<p align="center">
|
|
|
|
| 132 |
model = AutoModelForSeq2SeqLM.from_pretrained("HiTZ/Medical-mT5-large")
|
| 133 |
```
|
| 134 |
|
| 135 |
+
The model has been trained using the T5 masked language modelling tasks. You need to finetune the model for your task.
|
| 136 |
|
| 137 |
<p align="center">
|
| 138 |
<br>
|