Instructions to use klyang/MentaLLaMA-chat-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use klyang/MentaLLaMA-chat-13B with Transformers:

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

pipe = pipeline("text-generation", model="klyang/MentaLLaMA-chat-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("klyang/MentaLLaMA-chat-13B")
model = AutoModelForCausalLM.from_pretrained("klyang/MentaLLaMA-chat-13B", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use klyang/MentaLLaMA-chat-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "klyang/MentaLLaMA-chat-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "klyang/MentaLLaMA-chat-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/klyang/MentaLLaMA-chat-13B

SGLang

How to use klyang/MentaLLaMA-chat-13B 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 "klyang/MentaLLaMA-chat-13B" \
    --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": "klyang/MentaLLaMA-chat-13B",
		"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 "klyang/MentaLLaMA-chat-13B" \
        --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": "klyang/MentaLLaMA-chat-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use klyang/MentaLLaMA-chat-13B with Docker Model Runner:
```
docker model run hf.co/klyang/MentaLLaMA-chat-13B
```

klyang commited on Sep 27, 2023

Commit

3ca1890

1 Parent(s): 7a88fec

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -1

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ tags:
 - medical
 ---
-# MentaLLaMA-chat-13B
 MentaLLaMA-chat-13B is part of the [MentaLLaMA](https://github.com/SteveKGYang/MentalLLaMA) project, the first open-source large language model (LLM) series for
 interpretable mental health analysis with instruction-following capability. This model is finetuned based on the Meta LLaMA2-chat-13B foundation model and the full IMHI instruction tuning data.
@@ -17,6 +17,18 @@ It is fine-tuned on the IMHI dataset with 75K high-quality natural language inst
 We perform a comprehensive evaluation on the IMHI benchmark with 20K test samples. The result shows that MentalLLaMA approaches state-of-the-art discriminative
 methods in correctness and generates high-quality explanations.
 ## Other Models in MentaLLaMA
 In addition to MentaLLaMA-chat-13B, the MentaLLaMA project includes another model: MentaLLaMA-chat-7B, MentalBART, MentalT5.

 - medical
 ---
+# Introduction
 MentaLLaMA-chat-13B is part of the [MentaLLaMA](https://github.com/SteveKGYang/MentalLLaMA) project, the first open-source large language model (LLM) series for
 interpretable mental health analysis with instruction-following capability. This model is finetuned based on the Meta LLaMA2-chat-13B foundation model and the full IMHI instruction tuning data.
 We perform a comprehensive evaluation on the IMHI benchmark with 20K test samples. The result shows that MentalLLaMA approaches state-of-the-art discriminative
 methods in correctness and generates high-quality explanations.
+# Ethical Consideration
+Although experiments on MentaLLaMA show promising performance on interpretable mental health analysis, we stress that
+all predicted results and generated explanations should only used
+for non-clinical research, and the help-seeker should get assistance
+from professional psychiatrists or clinical practitioners. In addition,
+recent studies have indicated LLMs may introduce some potential
+bias, such as gender gaps. Meanwhile, some incorrect prediction results, inappropriate explanations, and over-generalization
+also illustrate the potential risks of current LLMs. Therefore, there
+are still many challenges in applying the model to real-scenario
+mental health monitoring systems.
 ## Other Models in MentaLLaMA
 In addition to MentaLLaMA-chat-13B, the MentaLLaMA project includes another model: MentaLLaMA-chat-7B, MentalBART, MentalT5.