GGUF
Inference Endpoints
conversational
nevril's picture
Update README.md
87d9dce verified
|
raw
history blame
3.16 kB
---
license: llama3.1
datasets:
- CalebE/new_mental_health_conversations_all1
- Amod/mental_health_counseling_conversations
base_model:
- unsloth/Meta-Llama-3.1-8B-Instruct
---
# CounselorChat (C2) — A Mental Health Conversational Assistant
## Overview
**CounselorChat (C2)** is a fine-tuned version of the [Llama 3.1 8B](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) model, designed as an experimental chatbot to offer quick mental health tips and support. This model is **not a substitute for professional mental health care** and should not replace consultation with a licensed specialist.
The name *CounselorChat* is not the best but it was suggested by the model itself during testing so... you know...
---
## Features
- **Base Model**: [Llama 3.1 8B](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct).
- **Training Process**:
- **Datasets**: Fine-tuned on a combination of:
- [CalebE/new_mental_health_conversations_all1](https://huggingface.co/datasets/CalebE/new_mental_health_conversations_all1)
- [Amod/mental_health_counseling_conversations](https://huggingface.co/datasets/Amod/mental_health_counseling_conversations)
- **Method**: One epoch of training using **Unsloth** at 16-bit precision.
- **Data Cleanup**: Deduplication and cleaning were performed to enhance the quality of training data.
---
## Deployment Options
1. **GGUF Quantized Model**: Published as an **8-bit GGUF quantized model**. Other quantization levels are available upon request.
2. **Modelfile for Ollama**: A **pre-configured Modelfile** for deployment on Ollama is also included, with a default context length of **8192 tokens**.
- To deploy, update the **`PATH_TO_MODEL`** at the beginning of the Modelfile to point to the GGUF file location.
- Then, run the following CLI command from the same directory as the Modelfile:
```bash
ollama create C2_llama3.1_8B_q8x8K --file OllamaModelfile_C2_llama31_8B_Q8x8K
```
3. **Other Deployment Options**: For alternative deployment setups or platforms, it is recommended to set the **SYSTEM prompt** to:
> *You are an AI counselor designed to provide compassionate, evidence-based mental health support. Offer helpful, non-judgmental guidance focusing on validated techniques. Avoid diagnosing conditions, or speculative or unsafe advice.*
---
## Intended Use
CounselorChat is designed to provide **quick, supportive mental health tips**. It can be used for:
- Offering general advice for stress management, mindfulness, and coping strategies.
- Engaging in non-clinical conversations.
**Disclaimer**: This model is an **experimental tool**. It is not licensed or intended to provide clinical counseling or medical advice. For serious mental health concerns, please seek the assistance of a trained mental health professional.
---
## Limitations
- The model is not equipped to handle emergencies or complex mental health cases.
- Responses are generated based on the training data and may lack the nuance of human judgment.
- While efforts have been made to clean and deduplicate the datasets, unintended biases or inaccuracies may persist.
---