TEST: rm qwen1.5_7b test

Author: littlegy

.github/workflows/api_eva.yml

@@ -134,4 +134,4 @@ jobs:
         if: always()
         run: |
           export workdir=$(pwd)
-          rm -rf $workdir/*
+          rm -rf $workdir/*

autotest/config.yaml

@@ -139,7 +139,6 @@ pytorch_chat_model:
     - Qwen/Qwen2.5-32B-Instruct
     - Qwen/Qwen2.5-72B-Instruct
     - Qwen/Qwen2-7B-Instruct
-    - Qwen/Qwen1.5-7B-Chat
     - Qwen/Qwen1.5-MoE-A2.7B-Chat
     - Qwen/Qwen2.5-VL-7B-Instruct
     - Qwen/Qwen2.5-VL-32B-Instruct
@@ -379,7 +378,6 @@ benchmark_model:
 
 
 evaluate_model:
-  - Qwen/Qwen1.5-7B-Chat
   - google/gemma-2-9b-it
   - google/gemma-2-27b-it
   - internlm/internlm2_5-7b-chat

autotest/evaluate/eval_config_base.py

@@ -25,7 +25,7 @@
         type=OpenAISDK,
         abbr=f'{MODEL_NAME}-lmdeploy-api',
         openai_api_base=API_BASE,
-        key='EMPTY',  
+        key='EMPTY',
         path=MODEL_PATH,
         meta_template=api_meta_template,
         max_out_len=2048,

autotest/evaluate/eval_config_chat.py

@@ -8,12 +8,10 @@
 
 datasets = sum([v for k, v in locals().items() if k.endswith('_datasets')], [])
 
-
 MODEL_NAME = 'Qwen2-7B-Instruct'
 MODEL_PATH = '/nvme/qa_test_models/Qwen/Qwen2-7B-Instruct'
 API_BASE = 'http://127.0.0.1:65525/v1'
 
-
 api_meta_template = dict(round=[
     dict(role='HUMAN', api_role='HUMAN'),
     dict(role='BOT', api_role='BOT', generate=True),
@@ -24,7 +22,7 @@
         type=OpenAISDK,
         abbr=f'{MODEL_NAME}-lmdeploy-api',
         openai_api_base=API_BASE,
-        key='EMPTY', 
+        key='EMPTY',
         path=MODEL_PATH,
         meta_template=api_meta_template,
         max_out_len=2048,

autotest/evaluate/test_api_evaluate_pytorch.py

@@ -11,7 +11,6 @@ def prepare_environment(request, config, worker_id):
     param = request.param
     model = param['model']
     backend = param['backend']
-    print(param['model'], param['backend'], param['extra'])
     model_path = config.get('model_path') + '/' + model
     pid, startRes = start_restful_api(config, param, model, model_path, backend, worker_id)
     yield param

autotest/evaluate/test_api_evaluate_turbomind.py

@@ -11,7 +11,6 @@ def prepare_environment(request, config, worker_id):
     param = request.param
     model = param['model']
     backend = param['backend']
-    print(param['model'], param['backend'], param['extra'])
     model_path = config.get('model_path') + '/' + model
     pid, startRes = start_restful_api(config, param, model, model_path, backend, worker_id)
     yield param

autotest/utils/evaluate_utils.py

@@ -160,4 +160,4 @@ def restful_test(config, run_id, prepare_environment, worker_id='gw0', port=DEFA
                        f'after 7200 seconds')
         return False, timeout_msg
     except Exception as e:
-        return False, f'Error during evaluation for {model_name}: {str(e)}'
+        return False, f'Error during evaluation for {model_name}: {str(e)}'