---
license: mit
language: multilingual
base_model: unsloth/Llama-3.2-1B-Instruct
quantized_by: prodoc.ai
tags:
  - conversational
  - healthcare
  - conversation-ending
  - LLM
widget:
  - text: "Jens Peter Hansen kommer fra Danmark"
---

# ProdocAI/EndConvo-health-1b-GGUF-v1

`EndConvo-health-1b-GGUF-v1` is a fine-tuned version of the `Llama3.2-1B` model, trained on a dataset of healthcare-related conversations with the purpose of identifying whether a conversation has ended. This model helps to avoid unnecessary responses from larger language models by detecting closing statements.

# Ollama Integration

Experience seamless integration with Ollama, where the model is fully hosted and ready to run. Simply execute the command `ollama run Prodoc/endconvo-health-1b` to start utilizing the model's capabilities in identifying conversation endpoints efficiently and effectively. Enjoy the ease of deployment and the power of advanced conversational analysis with Ollama.

## Model Details

- **Model Name**: `EndConvo-health-1b-GGUF-v1`
- **Base Model**: `Llama3.2-1B`
- **Number of Parameters**: 1 Billion
- **Dataset**: Custom dataset of 4,000 rows focused on healthcare conversations
- **Training Data Statistics**:
  - **Total Conversations**: 11,798
  - **Chat Count**: 94,472
  - **Average Chats per Conversation**: ~8
  - **Languages**: Includes `en`, `mr`, `te`, `hi`, `bn`, among others (detailed in Language Map section)

## Model Objective

The model identifies if a healthcare-related conversation has reached a natural conclusion to prevent unnecessary responses from a larger LLM. The model is trained to output:
- **True**: Conversation has ended.
- **False**: Conversation is still active.

## Dataset Overview

This healthcare-focused conversational dataset includes 11,798 unique conversations, with an average of 8 messages per conversation. The dataset consists of conversations in a variety of languages with the following breakdown:
  - **English** (`en`): 78,404 messages
  - **Marathi** (`mr`): 2,092 messages
  - **Hindi** (`hi`): 2,857 messages
  - ... and others as per the Language Map section.

### Example Input Format

Input to the model should be provided in the following format:

```plaintext
"Below is the conversation between the bot and user:

user: Please send me one bottle
bot: Hi, I am Vaidushi and how can I help you today regarding your interest to buy Madhavprash?
bot: Here is the link to purchase your Madhavprash https://madhavprash.store

user: 👆COD not possible here
bot: Currently, we do not support Cash on Delivery (COD) for purchases. You can complete your purchase using other available payment methods on our website.

bot: Thanks for your order, it will be delivered to you within 2-3 working days. Dosage Guidelines...
user: Thanks 🙏🤝 madam..... Kailas Varsekar ..."