feat: add deploy-and-train.sh script for server deployment

training/README.md

@@ -23,25 +23,24 @@ training/
 - GPU with 40GB+ VRAM (A100 recommended)
 - 64GB+ system RAM
 - 100GB+ free disk space
+- CUDA drivers installed
 
-## Installation
+## Server Deployment (Recommended)
+
+Use the deployment script to clone and train on your GPU server:
 
 ```bash
-cd scripts/lora_training/training
-
-# Create virtual environment
-python -m venv venv
-source venv/bin/activate
-
-# Install dependencies
-pip install transformers datasets trl peft accelerate bitsandbytes
-
-# Or use conda
-conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia
-pip install transformers datasets trl peft accelerate bitsandbytes
+# Deploy and train in one command
+bash deploy-and-train.sh
 ```
 
-## Usage
+This will:
+1. Clone the repo to `/opt/loras/agenx-lora-training`
+2. Setup Python environment with CUDA support
+3. Prepare the dataset
+4. Train the LoRA adapter
+
+## Manual Setup
 
 ### 1. Prepare Dataset
 
@@ -123,7 +122,3 @@ Trained model is saved to `output/llama2-7b-lora/`:
 **Generation too long/short:**
 - Adjust `max_new_tokens` in inference script
 - Tune `temperature` and `top_p`
-
-## License
-
-This training infrastructure is part of the AgenX project.