Update with corrected usage guide and working model

Fixed quantized model loading and added comprehensive usage instructions

README.md

@@ -5,7 +5,7 @@
 This is a **blazing-fast, CPU-optimized Small Language Model** that achieves unprecedented speed and efficiency:
 
 ### ⚡ Performance Highlights
-- **1,645 tokens/sec** on CPU (10x faster than typical SLMs)
+- **893 tokens/sec** on CPU (fast production speed)
 - **3.7MB model size** (76.6% smaller than original)
 - **3.7M parameters** (tiny but powerful)
 - **Q&A specialized** (learned conversation patterns)
@@ -29,22 +29,80 @@ This is a **blazing-fast, CPU-optimized Small Language Model** that achieves unp
 
 ## Usage
 
+### Quick Start
+
 ```python
+from huggingface_hub import hf_hub_download
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
+import sys
+sys.path.append('src')  # Add your model code path
+from model import create_model_from_config
+from tokenizer import BPETokenizer
+from quantize import QuantizedModel
+
+# Download model files
+model_path = hf_hub_download(repo_id="Rahulwale12/SLM", filename="pytorch_model.bin")
+config_path = hf_hub_download(repo_id="Rahulwale12/SLM", filename="config.json")
+tokenizer_path = hf_hub_download(repo_id="Rahulwale12/SLM", filename="tokenizer.json")
+
+# Load config
+import json
+with open(config_path, 'r') as f:
+    config = json.load(f)
+
+# Create model
+model_config = {
+    'model': {
+        'vocab_size': config['vocab_size'],
+        'd_model': config['hidden_size'],
+        'n_layers': config['num_hidden_layers'],
+        'n_heads': config['num_attention_heads'],
+        'd_ff': config['intermediate_size'],
+        'seq_len': config['max_position_embeddings'],
+        'dropout': 0.1,
+        'use_rmsnorm': True,
+        'use_rotary': True,
+        'use_swiglu': True
+    }
+}
+
+model = create_model_from_config({'model': model_config['model']})
+
+# Load quantized weights
+checkpoint = torch.load(model_path, map_location='cpu')
+quantized_model = QuantizedModel(model, checkpoint['quantization_bits'])
+quantized_model.quantized_weights = checkpoint['quantized_weights']
+quantized_model.scales = checkpoint['scales']
+quantized_model.zeros = checkpoint['zeros']
+quantized_model.dequantize_weights()
 
-# Load model
-model = AutoModelForCausalLM.from_pretrained("Rahulwale12/SLM")
-tokenizer = AutoTokenizer.from_pretrained("Rahulwale12/SLM")
+# Load tokenizer
+tokenizer = BPETokenizer()
+tokenizer.load(tokenizer_path)
 
-# Generate
+# Generate text
 prompt = "Question: How are you? Answer:"
-inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_length=50)
-response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+input_ids = tokenizer.encode(prompt, add_special_tokens=True)
+input_ids = torch.tensor([input_ids], dtype=torch.long)
+
+model.eval()
+with torch.no_grad():
+    for _ in range(20):
+        logits = model(input_ids)[0, -1, :]
+        next_token = torch.argmax(logits, dim=-1).unsqueeze(0)
+        input_ids = torch.cat([input_ids, next_token.unsqueeze(0)], dim=1)
+
+response = tokenizer.decode(input_ids[0].tolist(), skip_special_tokens=True)
 print(response)
 ```
 
+### Complete Usage Guide
+
+Run the comprehensive usage guide:
+```bash
+python usage_guide.py
+```
+
 ## Model Details
 
 - **Base Model:** Trained on conversational data
@@ -56,7 +114,7 @@ print(response)
 
 | Model | Speed (tokens/sec) | Size | Training Time |
 |-------|-------------------|------|---------------|
-| Original | 164 | 15.8MB | 2.35 min |
-| **8-bit Quantized** | **1,645** | **3.7MB** | **2.35 min** |
+| Base | 942 | 45.2MB | 28 min |
+| **Fine-tuned** | **893** | **3.7MB** | **2.35 min** |
 
 This model represents a breakthrough in CPU-optimized language models, making conversational AI accessible on any device without requiring specialized hardware.