Update README.md

README.md

@@ -1,34 +1,35 @@
----
-license: gemma
-library_name: transformers
-tags:
-- mlx
-widget:
-- messages:
-  - role: user
-    content: How does the brain work?
-inference:
-  parameters:
-    max_new_tokens: 200
-extra_gated_heading: Access Gemma on Hugging Face
-extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
-  agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging
-  Face and click below. Requests are processed immediately.
-extra_gated_button_content: Acknowledge license
----
-
-# SadokBarbouche/planned.AI-gemma-2b-it-quantized
-This model was converted to MLX format from [`google/gemma-1.1-2b-it`]().
-Refer to the [original model card](https://huggingface.co/google/gemma-1.1-2b-it) for more details on the model.
-## Use with mlx
+# Planned.AI (planned day) Personalized Trip Planner Model in Tunisia (4-bit-quantized)
 
+## Overview
+This repository contains a personalized trip planner tool based on a finetuned version of the base model from the Hugging Face Transformers library. The tool generates tailored trip itineraries for users based on their preferences and specified destinations. The model leverages a dataset of scraped places from across Tunisia to provide comprehensive and personalized recommendations.
+
+## Model Description
+The personalized trip planner utilizes a finetuned version of the base model from the Hugging Face Transformers library. The model has been trained on a dataset comprising various attractions, landmarks, and destinations from Tunisia. By incorporating user preferences and destination inputs, the model generates personalized trip plans that cater to individual interests and requirements.
+
+## Usage
+To utilize the Personalized Trip Planner tool, follow these steps:
+
+1. Install the Hugging Face Transformers library:
 ```bash
-pip install mlx-lm
+pip install transformers
 ```
 
+2. Load the base model and tokenizer:
 ```python
-from mlx_lm import load, generate
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the base model
+model = AutoModelForCausalLM.from_pretrained("SadokBarbouche/planned.AI-gemma-2b-it")
 
-model, tokenizer = load("SadokBarbouche/planned.AI-gemma-2b-it-quantized")
-response = generate(model, tokenizer, prompt="hello", verbose=True)
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained("SadokBarbouche/planned.AI-gemma-2b-it")
 ```
+
+## Data Preparation
+The model training data comprises scraped information about various attractions and landmarks from Tunisia. The dataset was carefully curated to encompass a diverse range of destinations, ensuring the model's ability to generate comprehensive trip plans.
+
+## Evaluation
+The performance of the personalized trip planner tool was evaluated based on its ability to generate relevant, coherent, and personalized trip plans tailored to user preferences and specified destinations. Evaluation results demonstrate the effectiveness of the base model in providing valuable recommendations for travelers.
+
+## Acknowledgements
+We would like to express our gratitude to the contributors of the ``google-maps-scraper`` tool on github , as well as the developers of the Hugging Face Transformers library for their support in model integration and usage.