Instructions to use Kush26/Mental_Health_ChatBot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kush26/Mental_Health_ChatBot with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Kush26/Mental_Health_ChatBot",
	filename="all_files/unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Kush26/Mental_Health_ChatBot with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Kush26/Mental_Health_ChatBot:F16
# Run inference directly in the terminal:
llama cli -hf Kush26/Mental_Health_ChatBot:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Kush26/Mental_Health_ChatBot:F16
# Run inference directly in the terminal:
llama cli -hf Kush26/Mental_Health_ChatBot:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Kush26/Mental_Health_ChatBot:F16
# Run inference directly in the terminal:
./llama-cli -hf Kush26/Mental_Health_ChatBot:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Kush26/Mental_Health_ChatBot:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kush26/Mental_Health_ChatBot:F16

Use Docker

docker model run hf.co/Kush26/Mental_Health_ChatBot:F16

LM Studio
Jan

vLLM

How to use Kush26/Mental_Health_ChatBot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kush26/Mental_Health_ChatBot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kush26/Mental_Health_ChatBot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kush26/Mental_Health_ChatBot:F16

Ollama
How to use Kush26/Mental_Health_ChatBot with Ollama:
```
ollama run hf.co/Kush26/Mental_Health_ChatBot:F16
```

Unsloth Studio

How to use Kush26/Mental_Health_ChatBot with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Kush26/Mental_Health_ChatBot to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Kush26/Mental_Health_ChatBot to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Kush26/Mental_Health_ChatBot to start chatting

Atomic Chat new
Docker Model Runner
How to use Kush26/Mental_Health_ChatBot with Docker Model Runner:
```
docker model run hf.co/Kush26/Mental_Health_ChatBot:F16
```

Lemonade

How to use Kush26/Mental_Health_ChatBot with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kush26/Mental_Health_ChatBot:F16

Run and chat with the model

lemonade run user.Mental_Health_ChatBot-F16

List all available models

lemonade list

Fine-Tuned LLaMA-3 8B Mental Health Conversational Model

Model Overview

This is a fine-tuned version of LLaMA-3 8B Instruct, specifically adapted for conversational mental health support. The model has been fine-tuned using LoRA / QLoRA techniques and quantized to 4-bit for efficient inference. It is ideal for applications requiring lightweight deployment without compromising the quality of responses.

Base Model: LLaMA-3 8B Instruct
Fine-Tuning: Mental health conversational dataset
Technique: LoRA / QLoRA
Quantization: 4-bit (GGUF)
File Format: model.Q4_K_M.gguf

This model is optimized for generating empathetic, safe, and context-aware responses for mental health conversations. It is intended for research, personal, or educational use.

How to Download

You can download the model using this link:

Using in LM Studio

Follow these steps to use the model in LM Studio:

Install LM Studio
Download and install LM Studio from https://lmstudio.ai.
Add the Model
- Open LM Studio.
- Click "Add Model" or "Load Local Model".
- Select the downloaded model.Q4_K_M.gguf file.
Configure Model Settings
- Choose appropriate context length (e.g., 2048 tokens).
- Enable GPU acceleration if available for faster inference.
- Adjust any sampling parameters (temperature, top-p) as needed.
Start Chatting
- Open a new chat session.
- Interact with the model for mental health conversations or research purposes.

Notes

This model is not a substitute for professional mental health care.
Use responsibly and ensure privacy when handling sensitive conversations.
Compatible with LM Studio version 1.9 and above.

Downloads last month: 34

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Model tree for Kush26/Mental_Health_ChatBot

Base model

unsloth/llama-3-8b-Instruct-bnb-4bit

Quantized

(660)

this model

Kush26
/

Mental_Health_ChatBot