|
--- |
|
license: llama3 |
|
datasets: |
|
- Ahmedelmorshidy/influraQAs |
|
language: |
|
- en |
|
metrics: |
|
- accuracy |
|
base_model: |
|
- TinyLlama/TinyLlama-1.1B-Chat-v1.0 |
|
new_version: Ahmedelmorshidy/influra_chatbot |
|
pipeline_tag: question-answering |
|
tags: |
|
- ads |
|
- chatbot |
|
- QAchatbots |
|
--- |
|
# Model Card for Model ID |
|
|
|
The Influra Chatbot is a fine-tuned version of the TinyLLaMA 1.1B model, created to deliver accurate, context-specific responses for the Influra app. This model has been trained using a custom dataset, Ahmedelmorshidy/influraQAs, |
|
designed to cover all aspects of the app, including features, functionalities, and user support. |
|
|
|
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
Model Overview |
|
Purpose |
|
This model powers the Influra chatbot, providing: |
|
|
|
Instant Support: Quick and accurate answers to user queries. |
|
Guidance: Helps users navigate the app and leverage its features effectively. |
|
Troubleshooting: Offers solutions to common issues encountered by users. |
|
Features |
|
Fine-tuned for Precision: Customized for Influra’s domain, ensuring relevant and reliable responses. |
|
Contextual Understanding: Delivers coherent, human-like interactions tailored to the app’s use cases. |
|
Lightweight and Efficient: Built on TinyLLaMA's architecture, combining speed with accuracy. |
|
Continuously Improving: Designed for updates with new data to enhance response quality over time. |
|
Performance |
|
The model exhibits high accuracy in domain-specific Q&A scenarios, validated through rigorous testing to ensure consistency and reliability. |
|
|
|
|
|
|
|
- **Developed by:** influra team |
|
|
|
|
|
- **Model type:** QA chatbot |
|
- **Language(s) (NLP):** english |
|
- **License:** [More Information Needed] |
|
- **Finetuned from model [optional]:** tinyllama 1.1b v1.0 |
|
### Model Sources [optional] |
|
|
|
|
|
## Uses |
|
|
|
for answering any question in app or about us |
|
|
|
|
|
## Training Details |
|
|
|
### Training Data |
|
|
|
Ahmedelmorshidy/influraQAs |
|
|
|
|
|
|
|
#### Training Hyperparameters |
|
|
|
- **Training regime:** [More Information Needed] bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype="float16" |
|
|
|
|
|
|
|
### Testing Data |
|
|
|
#### Testing Data |
|
|
|
Ahmedelmorshidy/influraQAs |
|
[More Information Needed] |
|
|
|
|
|
|
|
|
|
|
|
#### Summary |
|
This model has been fine-tuned specifically for the Influra app and is not intended for general-purpose language generation. For optimal performance, use it within the scope of Influra-related tasks. |
|
|
|
Influra – Empowering users with AI-driven support. |
|
|
|
|
|
|
|
|
|
|
