Instructions to use AIMH/mental-xlnet-base-cased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIMH/mental-xlnet-base-cased with Transformers:

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

pipe = pipeline("text-generation", model="AIMH/mental-xlnet-base-cased")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AIMH/mental-xlnet-base-cased")
model = AutoModelForCausalLM.from_pretrained("AIMH/mental-xlnet-base-cased")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AIMH/mental-xlnet-base-cased with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AIMH/mental-xlnet-base-cased

SGLang

How to use AIMH/mental-xlnet-base-cased 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 "AIMH/mental-xlnet-base-cased" \
    --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": "AIMH/mental-xlnet-base-cased",
		"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 "AIMH/mental-xlnet-base-cased" \
        --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": "AIMH/mental-xlnet-base-cased",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AIMH/mental-xlnet-base-cased with Docker Model Runner:
```
docker model run hf.co/AIMH/mental-xlnet-base-cased
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This model is pretrained from the checkpoint of xlnet-base-cased for the mental healthcare domain. XLNet model pre-trained on English language. It was introduced in the paper XLNet: Generalized Autoregressive Pretraining for Language Understanding by Yang et al. and first released in this repository.

Usage

Here is how to use this model to get the features of a given text in PyTorch:

from transformers import XLNetTokenizer, XLNetModel

tokenizer = XLNetTokenizer.from_pretrained('AIMH/mental-xlnet-base-cased')
model = XLNetModel.from_pretrained('AIMH/mental-xlnet-base-cased')

inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
outputs = model(**inputs)

last_hidden_states = outputs.last_hidden_state

To minimize the influence of worrying mask predictions, this model is gated. To download a gated model, you’ll need to be authenticated. Know more about gated models.

This model is biased due to training with posts about self-reported mental conditions and should not be used for text generation application, e.g., chatbot for mental health counseling.

Paper

@article{ji-domain-specific,
  author        = {Shaoxiong Ji and Tianlin Zhang and Kailai Yang and Sophia Ananiadou and Erik Cambria and J{\"o}rg Tiedemann},
  journal       = {arXiv preprint arXiv:2304.10447},
  title         = {Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health},
  year          = {2023},
  url           = {https://arxiv.org/abs/2304.10447}
}

Disclaimer

The model predictions are not psychiatric diagnoses. We recommend anyone who suffers from mental health issues to call the local mental health helpline and seek professional help if possible.

Downloads last month: -

Collection including AIMH/mental-xlnet-base-cased

MentalBERT series

Collection

Continue-pretrained encoder-only models for mental health • 10 items • Updated Nov 11, 2025

Papers for AIMH/mental-xlnet-base-cased

Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health

Paper • 2304.10447 • Published Apr 20, 2023 • 1

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Paper • 1906.08237 • Published Jun 19, 2019 • 1