initial commit
This commit is contained in:
85
batch_test.sh
Executable file
85
batch_test.sh
Executable file
@@ -0,0 +1,85 @@
|
||||
#!/bin/bash
|
||||
# Batch Test Script for AI Model Evaluation
|
||||
# Tests multiple models and generates comparison report
|
||||
|
||||
# Configuration
|
||||
ENDPOINT="${ENDPOINT:-http://localhost:11434}"
|
||||
API_KEY="${API_KEY:-}"
|
||||
|
||||
# Color output
|
||||
GREEN='\033[0;32m'
|
||||
BLUE='\033[0;34m'
|
||||
YELLOW='\033[1;33m'
|
||||
NC='\033[0m' # No Color
|
||||
|
||||
echo -e "${BLUE}========================================${NC}"
|
||||
echo -e "${BLUE}AI Model Batch Testing${NC}"
|
||||
echo -e "${BLUE}========================================${NC}"
|
||||
echo ""
|
||||
echo "Endpoint: $ENDPOINT"
|
||||
echo "API Key: ${API_KEY:0:10}${API_KEY:+...}"
|
||||
echo ""
|
||||
|
||||
# Function to run test
|
||||
run_test() {
|
||||
local model=$1
|
||||
echo -e "${GREEN}Testing: $model${NC}"
|
||||
|
||||
if [ -z "$API_KEY" ]; then
|
||||
python ai_eval.py --endpoint "$ENDPOINT" --model "$model"
|
||||
else
|
||||
python ai_eval.py --endpoint "$ENDPOINT" --api-key "$API_KEY" --model "$model"
|
||||
fi
|
||||
|
||||
if [ $? -eq 0 ]; then
|
||||
echo -e "${GREEN}✓ Completed: $model${NC}"
|
||||
else
|
||||
echo -e "${YELLOW}⚠ Failed or interrupted: $model${NC}"
|
||||
fi
|
||||
echo ""
|
||||
}
|
||||
|
||||
# Test qwen3:4b models with different quantizations
|
||||
echo -e "${BLUE}=== Testing qwen3:4b with different quantizations ===${NC}"
|
||||
echo ""
|
||||
|
||||
models_4b=(
|
||||
"qwen3:4b-q4_K_M"
|
||||
"qwen3:4b-q8_0"
|
||||
"qwen3:4b-fp16"
|
||||
)
|
||||
|
||||
for model in "${models_4b[@]}"; do
|
||||
run_test "$model"
|
||||
done
|
||||
|
||||
# Test different model sizes with q4_K_M quantization
|
||||
echo -e "${BLUE}=== Testing different model sizes (q4_K_M) ===${NC}"
|
||||
echo ""
|
||||
|
||||
models_sizes=(
|
||||
"qwen3:4b-q4_K_M"
|
||||
"qwen3:8b-q4_K_M"
|
||||
"qwen3:14b-q4_K_M"
|
||||
)
|
||||
|
||||
for model in "${models_sizes[@]}"; do
|
||||
run_test "$model"
|
||||
done
|
||||
|
||||
# Generate comparison report
|
||||
echo -e "${BLUE}========================================${NC}"
|
||||
echo -e "${BLUE}Generating Comparison Report${NC}"
|
||||
echo -e "${BLUE}========================================${NC}"
|
||||
echo ""
|
||||
|
||||
python analyze_results.py --compare
|
||||
python analyze_results.py --export batch_comparison.csv
|
||||
|
||||
echo ""
|
||||
echo -e "${GREEN}========================================${NC}"
|
||||
echo -e "${GREEN}Batch Testing Complete!${NC}"
|
||||
echo -e "${GREEN}========================================${NC}"
|
||||
echo ""
|
||||
echo "Results saved in ./results/"
|
||||
echo "Comparison CSV: ./results/batch_comparison.csv"
|
||||
Reference in New Issue
Block a user