Method quantize

utils/quantize_embeddings.py:46–125

Perform single quantization Args: embedding_type: Token embedding type (uppercase format, e.g., Q6_K) output_suffix: Output file suffix (lowercase format, e.g., q6_k) Returns: bool: Whether successful

(self, embedding_type, output_suffix)

        self.newly_created_files = set()  # Track newly created files
        
    def quantize(self, embedding_type, output_suffix):
        """
        Perform single quantization
        
        Args:
            embedding_type: Token embedding type (uppercase format, e.g., Q6_K)
            output_suffix: Output file suffix (lowercase format, e.g., q6_k)
        
        Returns:
            bool: Whether successful
        """
        output_file = self.output_dir / f"ggml-model-i2_s-embed-{output_suffix}.gguf"
        
        # Check if file already exists
        file_already_existed = output_file.exists()
        
        if file_already_existed:
            print(f"ℹ️  File already exists: {output_file}")
            print(f"   Skipping quantization, will use existing file for benchmark")
            return True
        
        cmd = [
            str(self.quantize_bin),
            "--token-embedding-type", embedding_type,
            str(self.input_model),
            str(output_file),
            "I2_S",
            "1",
            "1"
        ]
        
        print(f"\n{'='*80}")
        print(f"🔄 Quantizing with embedding type: {embedding_type}")
        print(f"📥 Input:  {self.input_model}")
        print(f"📤 Output: {output_file}")
        print(f"💻 Command: {' '.join(cmd)}")
        print(f"{'='*80}\n")
        
        start_time = datetime.now()
        
        try:
            result = subprocess.run(
                cmd,
                capture_output=True,
                text=True,
                cwd=os.getcwd(),
                timeout=600  # 10 minute timeout
            )
            
            end_time = datetime.now()
            duration = (end_time - start_time).total_seconds()
            
            if result.returncode == 0:
                # Get output file size
                file_size_mb = output_file.stat().st_size / (1024 * 1024)
                
                print(f"✅ Success! Duration: {duration:.2f}s, Size: {file_size_mb:.2f} MB")