run tests before mr

benchmarks/eval.py

@@ -9,7 +9,6 @@ Usage:
 Arguments:
     -m, --model           Specify the model to evaluate (e.g., "gpt-4", "qwen2.5:14b", etc.)
     -d, --dataset_file    Path to the dataset file (JSON or TSV) containing questions to evaluate
-    -o, --output_dir      Specify the output directory for results (default: "benchmarks/outputs/[benchmark_name]")
     -B, --backend         Backend to use: "openai", "openrouter", "ollama" (required)
     -e, --eval            Specify the evaluation benchmark
 

ci/benchmarks/.benchmarks.yml

@@ -19,16 +19,6 @@
         fi
       done
 
-    # to be removed 
-    - |
-      if [ "$BACKEND" = "ollama" ]; then
-        echo "Starting Ollama service..."
-        ollama serve &
-        sleep 10  # Give time for Ollama to start
-        curl http://localhost:8000/api/tags || echo "Ollama service may not be running properly"
-      fi
-    ## to be removed
-
 
     #- python3 benchmarks/cybermetric/CyberMetric_evaluator.py --model_name $MODEL_NAME --file_path $BENCHMARK_FILE
     - echo $OLLAMA_API_BASE