#!/bin/bash

cd llama.cpp
python3 convert_hf_to_gguf.py ../../osmosis-mcp-4b --outtype bf16
cd ..

# Input model file
INPUT_MODEL="osmosis-mcp-4B-BF16.gguf"

# Define quantization formats to generate
QUANT_FORMATS=(
    "Q4_K_S"
    "Q5_K_M"
    "Q5_K_S"
    "Q6_K"
    "IQ4_XS"
    "Q8_0"
    "Q2_K"
    "Q3_K_L"
    "Q3_K_M"
    "Q3_K_S"
    "Q4_K_M"
)

# Check if input model exists
if [ ! -f "$INPUT_MODEL" ]; then
    echo "Error: Input model file $INPUT_MODEL not found."
    exit 1
fi

# Path to llama-quantize tool
QUANTIZE_TOOL="llama.cpp/build/bin/llama-quantize"

# Check if quantize tool exists
if [ ! -f "$QUANTIZE_TOOL" ]; then
    echo "Error: Quantize tool not found at $QUANTIZE_TOOL"
    exit 1
fi

# Process each quantization format
for format in "${QUANT_FORMATS[@]}"; do
    echo "------------------------------------------------------"
    echo "Starting quantization: $format"
    echo "------------------------------------------------------"
    
    # Define output filename with the exact format requested
    OUTPUT_MODEL="osmosis-mcp-4b.${format}.gguf"
    
    # Check if output model already exists
    if [ -f "$OUTPUT_MODEL" ]; then
        echo "Model $OUTPUT_MODEL already exists. Skipping..."
        continue
    fi
    
    # Run quantization
    echo "Quantizing to $format..."
    "$QUANTIZE_TOOL" "$INPUT_MODEL" "$OUTPUT_MODEL" "$format"
    
    # Check if quantization was successful
    if [ $? -eq 0 ]; then
        echo "Successfully created $OUTPUT_MODEL"
    else
        echo "Failed to create $OUTPUT_MODEL"
    fi
    
    echo ""
done

echo "All quantizations completed!"
echo "Generated models:"
ls -lah osmosis-mcp-4b.*.gguf