Update README.md

README.md

@@ -1,18 +1,18 @@
 ---
-title: Flirt-AI with Phi-3-Mini (Base Model)
+title: thoshan_Flash
 emoji: 🐨
 colorFrom: yellow
 colorTo: purple
 sdk: gradio
 sdk_version: 5.45.0
 app_file: app.py
-pinned: false
+pinned: true
 license: mit
 ---
 
-# 💕 Flirt-AI with Phi-3-Mini - Complete Offline Package
+# 💕 thoshan_Flash - Complete Offline Package
 
-A conversational AI chatbot powered by Microsoft's Phi-3-mini model with a fun, flirty personality. This repository includes everything you need for offline development and training - no cloud dependencies required!
+A conversational Large language model with a fun, flirty personality. This repository includes everything you need for offline development and training - no cloud dependencies required!
 
 ## 🎁 What's Included
 
@@ -25,10 +25,11 @@ A conversational AI chatbot powered by Microsoft's Phi-3-mini model with a fun,
 ## 📦 Download & Quick Start
 
 ### Option 1: Clone Everything
+
 ```bash
 # Clone the complete repository
-git clone https://huggingface.co/spaces/lingadevaruhp/flirt-ai-gemma2-2b
-cd flirt-ai-gemma2-2b
+git clone https://huggingface.co/spaces/lingadevaruhp/thoshan_Flash_mini
+cd thoshan_Flash_mini
 
 # Install dependencies (one command, no conflicts)
 pip install transformers torch gradio accelerate
@@ -38,13 +39,15 @@ python app.py
 ```
 
 ### Option 2: Download Just the Dataset
+
 Get the dataset file directly for your own projects:
-- **Raw JSONL**: [flirt_dataset.jsonl](https://huggingface.co/spaces/lingadevaruhp/flirt-ai-gemma2-2b/raw/main/flirt_dataset.jsonl) 
+
+- **Raw JSONL**: [flirt_dataset.jsonl](https://huggingface.co/spaces/lingadevaruhp/thoshan_Flash_mini/raw/main/flirt_dataset.jsonl) 
 - **Direct download**: Right-click → "Save as" or use `wget`
 
 ```bash
 # Download dataset only
-wget https://huggingface.co/spaces/lingadevaruhp/flirt-ai-gemma2-2b/raw/main/flirt_dataset.jsonl
+wget https://huggingface.co/spaces/lingadevaruhp/thoshan_Flash_mini/raw/main/flirt_dataset.jsonl
 ```
 
 ## 🔥 Using the Dataset (Offline Training)
@@ -56,6 +59,7 @@ The `flirt_dataset.jsonl` file contains 20 flirty tech Q&A pairs in standard for
 ```
 
 ### Load in Python (Copy-Paste Ready)
+
 ```python
 import json
 
@@ -70,6 +74,7 @@ for item in dataset[:2]:  # Show first 2
 ```
 
 ### Use with Popular Training Libraries
+
 ```python
 # With Hugging Face datasets
 from datasets import load_dataset
@@ -92,7 +97,7 @@ with open('flirt_dataset.jsonl', 'r') as f:
 
 ## 💻 Model Information
 
-- **Base Model**: `microsoft/Phi-3-mini-4k-instruct`
+- **Base Model**: `thoshan_Flash`
 - **No fine-tuning required** - Works out of the box
 - **Public model** - No API keys or special access needed
 - **Lightweight** - Runs on consumer GPUs (4GB+ VRAM recommended)
@@ -101,6 +106,7 @@ with open('flirt_dataset.jsonl', 'r') as f:
 ## 🚀 Advanced Usage
 
 ### Custom Training with Your Data
+
 ```python
 # Combine with your own data
 my_data = []
@@ -120,12 +126,13 @@ with open('my_custom_dataset.jsonl', 'w') as f:
 ```
 
 ### Fine-tune Locally (Optional)
+
 ```python
 # Example fine-tuning setup (requires additional setup)
 from transformers import AutoTokenizer, AutoModelForCausalLM
 from transformers import TrainingArguments, Trainer
 
-model_name = "microsoft/Phi-3-mini-4k-instruct"
+model_name = "thoshan_Flash"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 
@@ -137,22 +144,26 @@ model = AutoModelForCausalLM.from_pretrained(model_name)
 ### Common Issues & Solutions
 
 **"Model not found"** → Check internet connection for first download
+
 ```bash
 pip install --upgrade transformers torch
 ```
 
 **"Out of memory"** → Reduce batch size or use CPU mode
+
 ```python
 # In app.py, add:
 device = "cpu"  # Force CPU usage
 ```
 
 **"Gradio won't start"** → Update Gradio
+
 ```bash
 pip install --upgrade gradio
 ```
 
 **"Dataset won't load"** → Verify file format
+
 ```bash
 # Check if file is valid JSON lines
 python -c "import json; [json.loads(line) for line in open('flirt_dataset.jsonl')]; print('Valid!')"
@@ -182,5 +193,4 @@ python -c "import json; [json.loads(line) for line in open('flirt_dataset.jsonl'
 - **Added**: Copy-paste ready code examples
 
 ---
-
 **Ready to get flirty with AI? Download, run, and start chatting! 💕**