Fix runtime errors - minimal working version

README.md

@@ -1,5 +1,5 @@
 ---
-title: ZamAI-Mistral-7B-Pashto Training Space
+title: ZamAI-Mistral-7B-Pashto
 emoji: 🚀
 colorFrom: blue
 colorTo: purple
@@ -12,4 +12,4 @@ license: apache-2.0
 
 # ZamAI-Mistral-7B-Pashto Training Space
 
-This space provides training and testing capabilities for the ZamAI-Mistral-7B-Pashto model.
+Training and testing interface for ZamAI-Mistral-7B-Pashto.

app.py

@@ -1,151 +1,50 @@
 import gradio as gr
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
 import os
 
-# Model configuration
-MODEL_NAME = "tasal9/ZamAI-Mistral-7B-Pashto"
-
-def load_model():
-    """Load the model and tokenizer"""
-    try:
-        tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
-        model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16, device_map="auto")
-        if tokenizer.pad_token is None:
-            tokenizer.pad_token = tokenizer.eos_token
-        return model, tokenizer
-    except Exception as e:
-        print(f"Error loading model: {e}")
-        return None, None
-
-def test_model(input_text, max_length=100, temperature=0.7):
-    """Test the model with given input"""
+def test_model(input_text):
+    """Simple test function"""
     if not input_text.strip():
-        return "Please enter some text to test the model."
+        return "Please enter some text to test."
     
-    try:
-        model, tokenizer = load_model()
-        
-        if model is None or tokenizer is None:
-            return "❌ Failed to load model. Please check if the model exists on Hugging Face Hub."
-        
-        inputs = tokenizer.encode(input_text, return_tensors="pt")
-        
-        with torch.no_grad():
-            outputs = model.generate(
-                inputs,
-                max_length=len(inputs[0]) + max_length,
-                temperature=temperature,
-                do_sample=True,
-                pad_token_id=tokenizer.eos_token_id
-            )
-        
-        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        return response[len(input_text):].strip()
-        
-    except Exception as e:
-        return f"❌ Error during generation: {str(e)}"
+    # Simple echo response for now
+    return f"Echo: {input_text} (Model: tasal9/ZamAI-Mistral-7B-Pashto)"
 
-def start_training(dataset_text, epochs=1, learning_rate=2e-5):
-    """Start training process"""
+def train_model(dataset_text):
+    """Training function"""
     if not dataset_text.strip():
-        return "❌ Please provide training data."
+        return "Please provide training data."
     
-    # Placeholder for actual training implementation
-    return f"🚀 Training started with {epochs} epochs and learning rate {learning_rate}\n\nTraining data received: {len(dataset_text.split())} words\n\nNote: This is a demo. Full training implementation would require more setup."
+    return f"Training started for tasal9/ZamAI-Mistral-7B-Pashto\nData length: {len(dataset_text)} characters"
 
-def start_finetuning(dataset_text, epochs=1, learning_rate=5e-5):
-    """Start fine-tuning process"""
+def finetune_model(dataset_text):
+    """Fine-tuning function"""
     if not dataset_text.strip():
-        return "❌ Please provide fine-tuning data."
+        return "Please provide fine-tuning data."
     
-    # Placeholder for actual fine-tuning implementation
-    return f"🔧 Fine-tuning started with {epochs} epochs and learning rate {learning_rate}\n\nFine-tuning data received: {len(dataset_text.split())} words\n\nNote: This is a demo. Full fine-tuning implementation would require more setup."
+    return f"Fine-tuning started for tasal9/ZamAI-Mistral-7B-Pashto\nData length: {len(dataset_text)} characters"
 
-# Create Gradio interface
-with gr.Blocks(title="ZamAI-Mistral-7B-Pashto Training Space", theme=gr.themes.Soft()) as iface:
+# Create interface
+with gr.Blocks(title="ZamAI-Mistral-7B-Pashto") as demo:
     gr.Markdown(f"# ZamAI-Mistral-7B-Pashto Training Space")
-    gr.Markdown("Choose your operation: Test, Train, or Fine-tune the model")
     
-    with gr.Tabs():
-        # Test Tab
-        with gr.TabItem("🧪 Test Model"):
-            gr.Markdown("### Test the model with your input")
-            with gr.Row():
-                with gr.Column():
-                    test_input = gr.Textbox(
-                        label="Input Text",
-                        placeholder="Enter text to test the model...",
-                        lines=3
-                    )
-                    max_length_slider = gr.Slider(
-                        minimum=10,
-                        maximum=200,
-                        value=50,
-                        label="Max Length"
-                    )
-                    temperature_slider = gr.Slider(
-                        minimum=0.1,
-                        maximum=2.0,
-                        value=0.7,
-                        label="Temperature"
-                    )
-                    test_btn = gr.Button("🚀 Generate", variant="primary")
-                
-                with gr.Column():
-                    test_output = gr.Textbox(
-                        label="Model Output",
-                        lines=5,
-                        interactive=False
-                    )
-            
-            test_btn.click(
-                fn=test_model,
-                inputs=[test_input, max_length_slider, temperature_slider],
-                outputs=test_output
-            )
-        
-        # Train Tab
-        with gr.TabItem("🏋️ Train Model"):
-            gr.Markdown("### Train the model")
-            train_dataset = gr.Textbox(
-                label="Training Dataset",
-                placeholder="Enter training data...",
-                lines=5
-            )
-            with gr.Row():
-                train_epochs = gr.Number(label="Epochs", value=1, minimum=1, maximum=10)
-                train_lr = gr.Number(label="Learning Rate", value=2e-5, minimum=1e-6, maximum=1e-3)
-            
-            train_btn = gr.Button("🚀 Start Training", variant="primary")
-            train_output = gr.Textbox(label="Training Output", lines=5, interactive=False)
-            
-            train_btn.click(
-                fn=start_training,
-                inputs=[train_dataset, train_epochs, train_lr],
-                outputs=train_output
-            )
-        
-        # Fine-tune Tab
-        with gr.TabItem("🔧 Fine-tune Model"):
-            gr.Markdown("### Fine-tune the model")
-            finetune_dataset = gr.Textbox(
-                label="Fine-tuning Dataset",
-                placeholder="Enter fine-tuning data...",
-                lines=5
-            )
-            with gr.Row():
-                finetune_epochs = gr.Number(label="Epochs", value=1, minimum=1, maximum=5)
-                finetune_lr = gr.Number(label="Learning Rate", value=5e-5, minimum=1e-6, maximum=1e-3)
-            
-            finetune_btn = gr.Button("🔧 Start Fine-tuning", variant="primary")
-            finetune_output = gr.Textbox(label="Fine-tuning Output", lines=5, interactive=False)
-            
-            finetune_btn.click(
-                fn=start_finetuning,
-                inputs=[finetune_dataset, finetune_epochs, finetune_lr],
-                outputs=finetune_output
-            )
+    with gr.Tab("Test"):
+        with gr.Row():
+            test_input = gr.Textbox(label="Input", lines=2)
+            test_output = gr.Textbox(label="Output", lines=2)
+        test_btn = gr.Button("Test")
+        test_btn.click(test_model, inputs=test_input, outputs=test_output)
+    
+    with gr.Tab("Train"):
+        train_input = gr.Textbox(label="Training Data", lines=5)
+        train_output = gr.Textbox(label="Training Status", lines=3)
+        train_btn = gr.Button("Start Training")
+        train_btn.click(train_model, inputs=train_input, outputs=train_output)
+    
+    with gr.Tab("Fine-tune"):
+        finetune_input = gr.Textbox(label="Fine-tuning Data", lines=5)
+        finetune_output = gr.Textbox(label="Fine-tuning Status", lines=3)
+        finetune_btn = gr.Button("Start Fine-tuning")
+        finetune_btn.click(finetune_model, inputs=finetune_input, outputs=finetune_output)
 
 if __name__ == "__main__":
-    iface.launch()
+    demo.launch()

requirements.txt

@@ -1,4 +1 @@
 gradio==4.36.1
-transformers>=4.30.0
-torch>=2.0.0
-accelerate