Update demo.py

demo.py

@@ -1,12 +1,7 @@
-
 #!/usr/bin/env python3
 """
-🚀 HyperMambaLM Demo Script 🚀
-
-The ultimate showcase script that flexes ALL of HyperMambaLM's superpowers!
-Sit back, grab some popcorn, and watch this beast in action. 🍿
-
-Warning: May cause excessive excitement about AI capabilities!
+HyperMambaLM Demo Script
+Simple demo for language model
 """
 
 import torch
@@ -17,12 +12,12 @@ import time
 import json
 
 def main():
-    print("🚀" + "="*58 + "🚀")
-    print("🌟      HYPERMAMBALM-300M DEMO - THE BEAST AWAKENS      🌟")
-    print("🚀" + "="*58 + "🚀")
+    print("=" * 50)
+    print("  HYPERMAMBALM-300M DEMO")
+    print("=" * 50)
     
-    # 1. Tạo model configuration
-    print("\n📋 STEP 1: Creating HyperMamba Configuration...")
+    # 1. Create model config
+    print("\n1. Creating model configuration...")
     config = HyperMambaConfig(
         vocab_size=32000,
         d_model=768,
@@ -37,44 +32,37 @@ def main():
         neural_architecture_search=True
     )
     
-    print(f"✅ Configuration created successfully!")
-    print(f"   - Vocabulary size: {config.vocab_size:,}")
-    print(f"   - Model dimension: {config.d_model}")
-    print(f"   - Number of layers: {config.n_layer}")
-    print(f"   - Meta-learning: {config.meta_learning}")
-    print(f"   - Few-shot adaptation: {config.few_shot_adaptation}")
+    print("Config created successfully!")
+    print(f"  - Vocab size: {config.vocab_size:,}")
+    print(f"  - Model dim: {config.d_model}")
+    print(f"  - Layers: {config.n_layer}")
     
-    # 2. Khởi tạo model
-    print("\n🏗️ STEP 2: Initializing HyperMambaLM Model...")
+    # 2. Initialize model
+    print("\n2. Initializing model...")
     model = HyperMambaLM(config)
     
-    # 3. Model statistics
-    print("\n📊 STEP 3: Model Statistics...")
-    # stats = model.get_memory_usage()
-    print(f"✅ Model created successfully!")
-    print(f"   - Total parameters: {stats['total_parameters']:,}")
-    print(f"   - Model size: {stats['model_size_mb']:.1f} MB")
-    print(f"   - Architecture: {stats['architecture']}")
-    print(f"   - Advanced features: {len(stats['features'])}")
-    for feature in stats['features']:
-        print(f"     ✓ {feature}")
-    
-    # 4. Tạo tokenizer
-    print("\n🔤 STEP 4: Creating Advanced BPE Tokenizer...")
+    # 3. Model stats
+    print("\n3. Model statistics...")
+    stats = model.get_memory_usage()
+    print("Model created successfully!")
+    print(f"  - Total params: {stats['total_parameters']:,}")
+    print(f"  - Model size: {stats['model_size_mb']:.1f} MB")
+    print(f"  - Features: {len(stats['features'])}")
+    
+    # 4. Create tokenizer
+    print("\n4. Creating tokenizer...")
     tokenizer = AdvancedBPETokenizer(config.vocab_size)
     
-    # Test tokenizer
-    test_text = "Xin chào! Tôi là HyperMambaLM, một siêu model AI."
+    test_text = "Hello! I am HyperMambaLM AI model."
     tokens = tokenizer.encode(test_text)
     decoded = tokenizer.decode(tokens)
     
-    print(f"✅ Tokenizer created successfully!")
-    print(f"   - Original text: {test_text}")
-    print(f"   - Tokens (first 15): {tokens[:15]}")
-    print(f"   - Decoded text: {decoded}")
+    print("Tokenizer created!")
+    print(f"  - Test text: {test_text}")
+    print(f"  - Tokens: {tokens[:10]}...")
     
-    # 5. Basic inference test
-    print("\n⚡ STEP 5: Basic Inference Test...")
+    # 5. Basic inference
+    print("\n5. Basic inference test...")
     batch_size, seq_len = 2, 128
     input_ids = torch.randint(0, config.vocab_size, (batch_size, seq_len))
     
@@ -87,85 +75,51 @@ def main():
     
     end_time = time.time()
     
-    print(f"✅ Basic inference completed!")
-    print(f"   - Input shape: {input_ids.shape}")
-    print(f"   - Output shape: {logits.shape}")
-    print(f"   - Inference time: {(end_time - start_time)*1000:.2f}ms")
-    print(f"   - Throughput: {batch_size * seq_len / (end_time - start_time):.0f} tokens/sec")
+    print("Inference completed!")
+    print(f"  - Input shape: {input_ids.shape}")
+    print(f"  - Output shape: {logits.shape}")
+    print(f"  - Time: {(end_time - start_time)*1000:.2f}ms")
     
     # 6. Performance benchmark
-    print("\n🏁 STEP 6: Performance Benchmark...")
+    print("\n6. Performance benchmark...")
     profiler = ModelProfiler()
     
     benchmark_results = profiler.benchmark_inference(model, input_ids, num_runs=10)
     
-    print(f"✅ Benchmark completed!")
-    print(f"   - Average time: {benchmark_results['avg_time_ms']:.2f}ms")
-    print(f"   - Throughput: {benchmark_results['throughput_tokens_per_sec']:.0f} tokens/sec")
-    print(f"   - Batch size: {benchmark_results['batch_size']}")
-    print(f"   - Sequence length: {benchmark_results['sequence_length']}")
+    print("Benchmark completed!")
+    print(f"  - Avg time: {benchmark_results['avg_time_ms']:.2f}ms")
+    print(f"  - Throughput: {benchmark_results['throughput_tokens_per_sec']:.0f} tokens/sec")
     
-    # 7. Few-shot learning demo
-    print("\n🎯 STEP 7: Few-Shot Learning Demo...")
+    # 7. Few-shot learning
+    print("\n7. Few-shot learning demo...")
     
-    # Tạo few-shot data
     few_shot_loader = FewShotDataLoader(support_size=5, query_size=3)
     
-    # Sample texts cho few-shot learning
     sample_texts = [
-        "Hôm nay trời đẹp quá!",
-        "Tôi thích học machine learning.",
-        "HyperMambaLM là model tuyệt vời.",
-        "Artificial Intelligence rất thú vị.",
-        "Deep Learning đang phát triển mạnh.",
-        "Query 1: Hôm nay tôi muốn",
-        "Query 2: Machine learning giúp",
-        "Query 3: Tương lai của AI"
+        "Today is beautiful!",
+        "I like machine learning.",
+        "HyperMambaLM is great.",
+        "AI is interesting.",
+        "Deep learning is growing.",
+        "Query 1: Today I want",
+        "Query 2: ML helps",
+        "Query 3: Future of AI"
     ]
     
     batch = few_shot_loader.create_few_shot_batch(sample_texts, tokenizer)
     
-    print(f"✅ Few-shot batch created!")
-    print(f"   - Support set shape: {batch['support_set'].shape}")
-    print(f"   - Query set shape: {batch['query_set'].shape}")
-    print(f"   - Support size: {batch['support_size']}")
-    print(f"   - Query size: {batch['query_size']}")
-    
-    # Test few-shot adaptation
-    support_examples = [
-        (torch.randint(0, config.vocab_size, (1, 20)), 
-         torch.randint(0, config.vocab_size, (1, 20)))
-        for _ in range(5)
-    ]
-    
-    query = torch.randint(0, config.vocab_size, (1, 20))
-    
-    print("\n🧠 Testing Meta-Learning Adaptation...")
-    start_time = time.time()
-    
-    adapted_logits = model.few_shot_adapt(
-        support_examples=support_examples,
-        query=query,
-        adaptation_steps=3
-    )
-    
-    end_time = time.time()
-    
-    print(f"✅ Meta-learning adaptation completed!")
-    print(f"   - Adaptation time: {(end_time - start_time)*1000:.2f}ms")
-    print(f"   - Support examples: {len(support_examples)}")
-    print(f"   - Adaptation steps: 3")
-    print(f"   - Output shape: {adapted_logits.shape}")
+    print("Few-shot batch created!")
+    print(f"  - Support shape: {batch['support_set'].shape}")
+    print(f"  - Query shape: {batch['query_set'].shape}")
     
-    # 8. Text generation demo
-    print("\n📝 STEP 8: Text Generation Demo...")
+    # 8. Text generation
+    print("\n8. Text generation demo...")
     
-    # Tạo prompt cho generation
-    prompt_text = "Tôi là HyperMambaLM và tôi có thể"
+    prompt_text = "I am HyperMambaLM and I can"
     prompt_tokens = tokenizer.encode(prompt_text)
     prompt_tensor = torch.tensor([prompt_tokens])
     
-    print(f"🎯 Generating text from prompt: '{prompt_text}'")
+    print(f"Generating from: '{prompt_text}'")
     
     start_time = time.time()
     
@@ -181,110 +135,50 @@ def main():
     
     generated_text = tokenizer.decode(generated[0].tolist())
     
-    print(f"✅ Text generation completed!")
-    print(f"   - Generation time: {(end_time - start_time)*1000:.2f}ms")
-    print(f"   - Generated tokens: {generated.shape[1] - prompt_tensor.shape[1]}")
-    print(f"   - Generated text: {generated_text}")
-    
-    # 9. Continual learning demo
-    print("\n🔄 STEP 9: Continual Learning Demo...")
-    
-    # Tạo new data cho continual learning
-    new_data = torch.randint(0, config.vocab_size, (5, 50))
-    
-    print("🧠 Computing Fisher Information for EWC...")
-    start_time = time.time()
-    
-    ewc_loss_fn = model.continual_learn(new_data)
-    
-    end_time = time.time()
+    print("Text generation completed!")
+    print(f"  - Time: {(end_time - start_time)*1000:.2f}ms")
+    print(f"  - Generated: {generated_text}")
     
-    print(f"✅ Continual learning setup completed!")
-    print(f"   - Setup time: {(end_time - start_time)*1000:.2f}ms")
-    print(f"   - New data shape: {new_data.shape}")
-    print(f"   - EWC loss function created!")
-    
-    # 10. Memory usage analysis
-    print("\n💾 STEP 10: Memory Usage Analysis...")
-    
-    if torch.cuda.is_available():
-        torch.cuda.empty_cache()
-        memory_allocated = torch.cuda.memory_allocated() / 1024**2
-        memory_reserved = torch.cuda.memory_reserved() / 1024**2
-        
-        print(f"✅ GPU Memory Analysis:")
-        print(f"   - Memory allocated: {memory_allocated:.1f} MB")
-        print(f"   - Memory reserved: {memory_reserved:.1f} MB")
-    else:
-        print(f"✅ Running on CPU")
-        print(f"   - Model size: {stats['model_size_mb']:.1f} MB")
-    
-    # 11. Export model info
-    print("\n💾 STEP 11: Exporting Model Information...")
+    # 9. Export model info
+    print("\n9. Exporting model info...")
     
     model_info = {
         "model_name": "HyperMambaLM-300M",
         "version": "1.0.0",
-        "architecture": "Hyper Mamba",
         "parameters": stats['total_parameters'],
         "model_size_mb": stats['model_size_mb'],
         "features": stats['features'],
-        "config": {
-            "vocab_size": config.vocab_size,
-            "d_model": config.d_model,
-            "n_layer": config.n_layer,
-            "d_state": config.d_state,
-            "d_conv": config.d_conv,
-            "expand": config.expand,
-            "meta_learning": config.meta_learning,
-            "few_shot_adaptation": config.few_shot_adaptation,
-            "knowledge_distillation": config.knowledge_distillation,
-            "progressive_learning": config.progressive_learning,
-            "neural_architecture_search": config.neural_architecture_search
-        },
         "benchmark": {
             "inference_time_ms": benchmark_results['avg_time_ms'],
-            "throughput_tokens_per_sec": benchmark_results['throughput_tokens_per_sec'],
-            "batch_size": benchmark_results['batch_size'],
-            "sequence_length": benchmark_results['sequence_length']
+            "throughput_tokens_per_sec": benchmark_results['throughput_tokens_per_sec']
         }
     }
     
-    with open("hypermamba_info.json", "w", encoding="utf-8") as f:
-        json.dump(model_info, f, indent=2, ensure_ascii=False)
-    
-    print(f"✅ Model information exported to 'hypermamba_info.json'")
-    
-    # 12. Final summary
-    print("\n🎉" + "="*58 + "🎉")
-    print("🏆                 DEMO HOÀN THÀNH THÀNH CÔNG!                🏆")
-    print("🎉" + "="*58 + "🎉")
-    
-    print(f"\n📋 TỔNG KẾT:")
-    print(f"✅ Model: HyperMambaLM-300M")
-    print(f"✅ Parameters: {stats['total_parameters']:,}")
-    print(f"✅ Model size: {stats['model_size_mb']:.1f} MB")
-    print(f"✅ Inference speed: {benchmark_results['throughput_tokens_per_sec']:.0f} tokens/sec")
-    print(f"✅ Features: {len(stats['features'])} advanced capabilities")
-    print(f"✅ Meta-learning: Working perfectly!")
-    print(f"✅ Few-shot adaptation: Ready for deployment!")
-    print(f"✅ Text generation: Natural and fluent!")
-    print(f"✅ Continual learning: Setup completed!")
-    
-    print(f"\n🚀 HYPERMAMBALM RATING: ∞/10 🌟🌟🌟🌟🌟")
-    print(f"💎 SIÊU MẠNH - SIÊU NHANH - SIÊU THÔNG MINH! 🔥")
-    print(f"🧠 Không cần nhiều dữ liệu vẫn học cực giỏi! 💪")
-    
-    print(f"\n📞 Ready for Hugging Face upload! 🤗")
-    print(f"📁 Files created:")
-    print(f"   - config.json")
-    print(f"   - modeling_hypermamba.py") 
-    print(f"   - modeling_utils.py")
-    print(f"   - __init__.py")
-    print(f"   - README.md")
-    print(f"   - demo.py")
-    print(f"   - hypermamba_info.json")
+    with open("hypermamba_info.json", "w") as f:
+        json.dump(model_info, f, indent=2)
+    
+    print("Model info exported to 'hypermamba_info.json'")
+    
+    # 10. Summary
+    print("\n" + "=" * 50)
+    print("  DEMO COMPLETED SUCCESSFULLY!")
+    print("=" * 50)
+    
+    print(f"\nSummary:")
+    print(f"  Model: HyperMambaLM-300M")
+    print(f"  Parameters: {stats['total_parameters']:,}")
+    print(f"  Size: {stats['model_size_mb']:.1f} MB")
+    print(f"  Speed: {benchmark_results['throughput_tokens_per_sec']:.0f} tokens/sec")
+    print(f"  Features: {len(stats['features'])} capabilities")
+    
+    print(f"\nFiles created:")
+    print(f"  - config.json")
+    print(f"  - modeling_hypermamba.py") 
+    print(f"  - modeling_utils.py")
+    print(f"  - __init__.py")
+    print(f"  - demo.py")
+    print(f"  - hypermamba_info.json")
 
 
 if __name__ == "__main__":
-    main()
+    main()