Instructions to use MindIntLab/Psyche-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MindIntLab/Psyche-R1 with Transformers:

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

pipe = pipeline("text-generation", model="MindIntLab/Psyche-R1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MindIntLab/Psyche-R1")
model = AutoModelForCausalLM.from_pretrained("MindIntLab/Psyche-R1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MindIntLab/Psyche-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MindIntLab/Psyche-R1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MindIntLab/Psyche-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MindIntLab/Psyche-R1

SGLang

How to use MindIntLab/Psyche-R1 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 "MindIntLab/Psyche-R1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MindIntLab/Psyche-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "MindIntLab/Psyche-R1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MindIntLab/Psyche-R1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MindIntLab/Psyche-R1 with Docker Model Runner:
```
docker model run hf.co/MindIntLab/Psyche-R1
```

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.

Psyche-R1

[ACL 2026] Repositories for our paper: Psyche-r1: Towards reliable psychological llms through unified empathy, expertise, and reasoning

We propose the first Chinese psychological reasoning LLM that unifies empathy, expertise, and reasoning.

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on our proposed dataset encompassing psychological questions paired with detailed rationales, and empathetic single-turn dialogues.

We conduct a hybrid training strategy, including SFT and GRPO training. We will present detailed training hyperparameters later.

It achieves comparable performance to DeepSeek-R1 on several psychology benchmarks, including psychology counselor examination benchmark (PCEB) proposed by Hu et al. (2024), and CPsyExam test set proposed by Zhao et al. (2024). It also demonstates better performance in empathy on SoulChat2.0 test set (Xie et al. 2025).

Training procedure

SFT Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 16
total_train_batch_size: 256
total_eval_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2.0

GRPO Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-06
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 128
total_eval_batch_size: 8
ppo_mini_batch_size: 32
ppo_micro_batch_size_per_gpu: 20
kl_loss_coef: 0.001
lr_scheduler_warmup_steps: 10
num_epochs: 2.0

Usage

For quick start, please see MindIntLab-HFUT/Psyche-R1 on GitHub.

Citation

If this work is helpful, please kindly cite as:

@misc{dai2025psycher1reliablepsychologicalllms,
      title={Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning}, 
      author={Chongyuan Dai and Jinpeng Hu and Hongchang Shi and Zhuo Li and Xun Yang and Meng Wang},
      year={2025},
      eprint={2508.10848},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.10848}, 
}