Instructions to use thrishala/mental_health_chatbot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thrishala/mental_health_chatbot with Transformers:

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

pipe = pipeline("text-generation", model="thrishala/mental_health_chatbot")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thrishala/mental_health_chatbot")
model = AutoModelForCausalLM.from_pretrained("thrishala/mental_health_chatbot")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use thrishala/mental_health_chatbot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/thrishala/mental_health_chatbot

SGLang

How to use thrishala/mental_health_chatbot 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 "thrishala/mental_health_chatbot" \
    --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": "thrishala/mental_health_chatbot",
		"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 "thrishala/mental_health_chatbot" \
        --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": "thrishala/mental_health_chatbot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use thrishala/mental_health_chatbot with Docker Model Runner:
```
docker model run hf.co/thrishala/mental_health_chatbot
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

This model is a fine-tuned version of the Llama 2 model ("NousResearch/Llama-2-7b-chat-hf") using a personalized dataset for a virtual therapy chatbot. The model is designed to assist users in providing mental health support through conversations that mimic real-world therapy interactions.

Model Details

Model Description

TThis model is a fine-tuned version of the Llama 2 base model, specifically designed for a chatbot to assist in virtual therapy and mental health counseling. It has been fine-tuned with a dataset of responses from real-world therapy interactions, focusing on providing personalized, empathetic replies. The model is trained using the Quantized Low-Rank Adaptation (QLoRA) technique for efficient fine-tuning.

Developed by: [More Information Needed]
Model type: LLM
Language(s) : NLP
Finetuned from model [optional]: NousResearch/Llama-2-7b-chat-hf

Model Sources [optional]

Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

Uses

The model is intended to be used as a virtual mental health support tool. It provides personalized, context-aware responses for individuals seeking help with issues such as anxiety, stress, relationships, and personal growth.

Direct Use

The model can be used for chatbot applications where users engage in conversations seeking therapeutic or emotional support. It is especially suited for mental health contexts where empathy and personalization are key.

[More Information Needed]

Downstream Use [optional]

The model can be fine-tuned further for specific mental health tasks, such as Cognitive Behavioral Therapy (CBT) or mindfulness coaching. It could also be integrated into apps or services where mental health support is needed.

[More Information Needed]

Out-of-Scope Use

The model should not be used for making medical diagnoses or providing crisis intervention support. It is not designed to replace professional therapy and is intended as a support tool, not a primary care option.

[More Information Needed]

Bias, Risks, and Limitations

This model, like any AI-based therapy chatbot, has limitations. It might not always fully understand the context of user conversations, and there may be biases based on the training data. The model also has limitations in dealing with complex or crisis situations.

[More Information Needed]

Recommendations

Users of the model should ensure that it is clear to end-users that the chatbot is not a substitute for professional mental health care. Monitoring for sensitive or high-risk conversations is recommended, and appropriate actions should be taken when the model encounters issues beyond its scope.

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Downloads last month: 12

Safetensors

Model size

7B params

Tensor type

F16

Model tree for thrishala/mental_health_chatbot

Quantizations

2 models

Spaces using thrishala/mental_health_chatbot 7

Paper for thrishala/mental_health_chatbot

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 47