Method quantize_embedding

utils/test_perplexity.py:241–312

Quantize model with specific embedding type. Args: embedding_type: Token embedding type (uppercase, e.g., 'Q6_K') output_suffix: Output file suffix (lowercase, e.g., 'q6_k') Returns: Path to quantized model or None if fai

(self, embedding_type, output_suffix)

        return None
    
    def quantize_embedding(self, embedding_type, output_suffix):
        """
        Quantize model with specific embedding type.
        
        Args:
            embedding_type: Token embedding type (uppercase, e.g., 'Q6_K')
            output_suffix: Output file suffix (lowercase, e.g., 'q6_k')
        
        Returns:
            Path to quantized model or None if failed
        """
        # Construct output path
        model_dir = self.model_path.parent
        output_path = model_dir / f"ggml-model-i2_s-embed-{output_suffix}.gguf"
        
        # Check if file already exists
        file_existed = output_path.exists()
        
        if file_existed:
            print(f"ℹ️  Model already exists: {output_path.name}")
            return output_path
        
        cmd = [
            str(self.quantize_bin),
            "--token-embedding-type", embedding_type,
            str(self.model_path),
            str(output_path),
            "I2_S",
            "1",
            "1"
        ]
        
        print(f"\n{'='*80}")
        print(f"🔄 Quantizing with embedding type: {embedding_type}")
        print(f"📥 Input:  {self.model_path.name}")
        print(f"📤 Output: {output_path.name}")
        print(f"💻 Command: {' '.join(cmd)}")
        print(f"{'='*80}\n")
        
        start_time = time.time()
        
        try:
            result = subprocess.run(
                cmd,
                capture_output=True,
                text=True,
                cwd=os.getcwd(),
                timeout=600  # 10 minutes timeout
            )
            
            duration = time.time() - start_time
            
            if result.returncode == 0:
                file_size_mb = output_path.stat().st_size / (1024 * 1024)
                print(f"✅ Quantization successful!")
                print(f"   Duration: {duration:.2f}s")
                print(f"   Size: {file_size_mb:.2f} MB")