sperate main.py to lm_eval and bigcode_eval

Signed-off-by: changwangss <[email protected]>

GenAIEval/evaluation/bigcode_evaluation_harness/main.py

@@ -0,0 +1,27 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (c) 2022 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from GenAIEval.evaluation.bigcode_evaluation_harness import evaluate, setup_parser
+
+
+def main():
+    eval_args = setup_parser()
+    results = evaluate(eval_args)
+    print(results)
+
+
+if __name__ == "__main__":
+    main()

main.py → GenAIEval/evaluation/lm_evaluation_harness/main.py

@@ -16,8 +16,6 @@
 # limitations under the License.
 from GenAIEval.evaluation.lm_evaluation_harness import evaluate, setup_parser
 
-# from GenAIEval.evaluation.bigcode_evaluation_harness import evaluate, setup_parser
-
 
 def main():
     eval_args = setup_parser()

README.md

@@ -16,7 +16,7 @@ For evaluating the models on text-generation tasks, we follow the [lm-evaluation
 ```shell
 
 # pip install --upgrade-strategy eager optimum[habana]
-
+cd GenAIEval/evaluation/lm_evaluation_harness
 python main.py \
     --model gaudi-hf \
     --model_args pretrained=EleutherAI/gpt-j-6B \
@@ -28,6 +28,8 @@ python main.py \
 
 ##### CPU
 ```shell
+
+cd GenAIEval/evaluation/lm_evaluation_harness
 python main.py \
     --model hf \
     --model_args pretrained=EleutherAI/gpt-j-6B \
@@ -53,12 +55,9 @@ results = evaluate(args)
 ### bigcode-evaluation-harness
 For evaluating the models on coding tasks or specifically coding LLMs, we follow the [bigcode-evaluation-harness](https://github.com/bigcode-project/bigcode-evaluation-harness) and provide the command line usage and function call usage. [HumanEval](https://huggingface.co/datasets/openai_humaneval), [HumanEval+](https://huggingface.co/datasets/evalplus/humanevalplus), [InstructHumanEval](https://huggingface.co/datasets/codeparrot/instructhumaneval), [APPS](https://huggingface.co/datasets/codeparrot/apps), [MBPP](https://huggingface.co/datasets/mbpp), [MBPP+](https://huggingface.co/datasets/evalplus/mbppplus), and [DS-1000](https://github.com/HKUNLP/DS-1000/) for both completion (left-to-right) and insertion (FIM) mode are available.
 #### command line usage
-There is a small code change in `main.py` regarding the import path.
-```diff
-- from GenAIEval.evaluation.lm_evaluation_harness import evaluate, setup_parser
-+ from GenAIEval.evaluation.bigcode_evaluation_harness import evaluate, setup_parser
-```
+
 ```shell
+cd GenAIEval/evaluation/bigcode_evaluation_harness
 python main.py \
     --model "codeparrot/codeparrot-small" \
     --tasks "humaneval" \