Repository files navigation

CodeFuseEval is a Code Generation benchmark that combines the multi-tasking scenarios of CodeFuse Model with the benchmarks of HumanEval-x and MBPP. This benchmark is designed to evaluate the performance of models in various multi-tasking tasks, including code completion, code generation from natural language, test case generation, cross-language code translation, and code generation from Chinese commands, among others.Continuously open, stay tuned !

CodeFuse-13B: Python 3.8 or above,PyTorch 1.12 or above, with a recommendation for 2.0 or above, Transformers 4.24.0 or above ,CUDA 11.4 or above (for GPU users and flash-attention users, this option should be considered).

CodeFuse-CodeLlama-34B:python>=3.8,pytorch>=2.0.0,transformers==4.32.0,Sentencepiece,CUDA 11.

The evaluation of the generated codes involves compiling and running in multiple programming languages. The versions of the programming language environments and packages we use are as follows:

In order to save everyone the trouble of setting up the environments for these languages, we create a Docker image with the required environments and codefuseEval.

docker pull registry.cn-hangzhou.aliyuncs.com/codefuse/codefuseeval:latest

If you are familiar with docker, you can build the image fromcodefuseEval/docker/Dockerfile or configure the Dockerfile as you like it:

cd codefuseEval/dockerdocker build [OPTIONS].

After obtaining the image, you can build a container using the following command:

docker run -it --gpus all --mount type=bind,source=<LOCAL PATH>,target=<PATH IN CONTAINER> [OPTIONS]<IMAGE NAME:TAG>

We provide the script to check the result for provided code LLMs. Please use following scripts to check corresponding results and the environment .

bash codefuseEval/script/check_reference.sh codefuseEval/result/CodeFuse-CodeLlama-34B/humaneval_result_python.jsonl humaneval_pythonbash codefuseEval/script/check_reference.sh codefuseEval/result/CodeFuse-13B/humaneval_result_python.jsonl humaneval_python

1. Download the model and update current model infomation in ckpt_config.json. Mainly update 「path」parameter in corresponding model and version.
2. Run following generation comand to generate result.

bash codefuseEval/script/generation.sh MODELNAME MODELVERSION EVALDATASET OUTFILE eg:bash codefuseEval/script/generation.sh CodeFuse-13B v1 humaneval_python result/test.jsonl

3. Run following evaluation command to evaluate the generated result for corresponding model and version.

bash codefuseEval/script/evaluation.sh <RESULT_FILE> <METRIC> <PROBLEM_FILE>eg: bash codefuseEval/script/evaluation.sh codefuseEval/result/test.jsonl pass@k humaneval_python

We recommend evaluating inthe provided image. To evaluate the generated samples, save generated codes in the following JSON list format:

{"task_id": "../..", "generation: "..."}{"task_id": "../..", "generation: "..."}...

and evaluate them using the following script under the root directory of the repository (please execute with caution, the generated codes might have unexpected behaviours though with very low possibility. See the warnings inexecution.py and uncomment the execution lines at your own risk):

Data are stored incodefuseEval/data, using JSON list format. We first integrated humaneval-X dataset.

• task_id: indicates the target language and ID of the problem. Language is one of ["Python", "Java", "JavaScript", "CPP", "Go"].
• prompt: the function declaration and docstring, used for code generation.
• declaration: only the function declaration, used for code translation.
• canonical_solution: human-crafted example solutions.
• test: hidden test samples, used for evaluation
• example_test: public test samples (appeared in prompt), used for evaluation.
• prompt_text: prompt text
• prompt_explain: prompt explanation
• func_title: code function title
• prompt_text_chinese: Chinese prompt

In addition to the unbiased pass@k indicators currently provided inCodex, we will also integrate the relevant indicators of huggingface open source withCodeBLEU for integration.The main indicators currently recommended for users are as follows:

• codebleu
• pass@k
• bleu
• bleurt

For other related metrics, you can check the code of the metric or the evaluation code to meet your requirements.

At the same time, we supplemented the indicators of the total and average generation time of the model for the datasettotal_time_cost andAverage time cost

Output during each generation, making it convenient for users to measure the generation performance of the model in the same environment. This indicator is passive output, and it will be output every time it is generated.

bash codefuseEval/script/evaluation.sh <RESULT_FILE> <METRIC> <PROBLEM_FILE> <TEST_GROUDTRUTH>eg: bash codefuseEval/script/evaluation.sh codefuseEval/result/test.jsonl pass@k humaneval_python

At the same time, we currently provide the following flags, which can directly bring the sample answers in the test data set as generated answers for testing.

• TEST_GROUDTRUTH default False

When TEST_GROUDTRUTH is True, the self-test mode is turned on, PROBLEM_FILE will be read, and the sample answer will be substituted as the generated answer for testing.

When TEST_GROUDTRUTH is False, open the evaluation mode, read RESULT_FILE and PROBLEM_FILE, and substitute the generated answer for testing.

1. Registry your evaluate dataset.

• Download evaluation dataset to store incodefuseEval/data or other directory. Dataset must be jsonl.
• Setup information datasetEVAL_DATASET,DATASET_SUPPORT andDATASET_LANGUAGE incodefuseEval/util.py for dataset path, dataset task_mode and generation code language

2. Registry your evaluate model.

• Download evaluation model to store incodefuseEval/model or other directory.
• Write your evaluation model processor code incodefuseEval/processor package.

We designed an infrastructure called Processor. Its main purpose is to handle the differences between different models. It mainly needs to complete three abstract functions:

• load_model_tokenizer:Due to differences in model loading parameters and tokenizer terminators, models need to use different parameters for adaptation and loading. The current function is mainly to help users load and adapt different models.
• process_before: Since prompt adapts to different prompt styles according to different types of evaluation tasks or different models selected by users, the 「process_before」function is extracted mainly to help users process prompts.
• process_after:Due to the diversity of model generation results, in order to adapt to the evaluation framework, the generated result data can be spliced into appropriate use cases for automated operation. The current function mainly processes the generated results to adapt to the evaluation data set and results based on the task type and data set conditions.

You can extend theBaseProcessor incodefuseEval/processor/base.py and implement above functions

• Setup information model inckpt_config.json. For Example as follow

{  "CodeFuse-13B": {     //model name    "v1": {             //model version      "path": "/mnt/model/CodeFuse13B-evol-instruction-4K/",       // model path      "processor_class": "codefuseEval.process.codefuse13b.Codefuse13BProcessor",  // model processor      "tokenizer": {                 // tokenizer params to token input string.        "truncation": true,        "padding": true,        "max_length": 600      },      "generation_config": {        //generation config params.         "greedy": {                 //If JsonObject, it is a decode mode, you can set 「decode_mode」param to load params defined in the decode_mode.          "do_sample": false,          "num_beams": 1,          "max_new_tokens": 512        },        "beams": {          "do_sample": false,          "num_beams": 5,          "max_new_tokens": 600,          "num_return_sequences": 1        },        "dosample": {          "da_sample": true        },        "temperature": 0.2,          //If not JsonObject, it is a default param, we will set in generation_config default. You can cover param in decode_mode same name param.        "max_new_tokens": 600,        "num_return_sequences": 1,        "top_p": 0.9,        "num_beams": 1,        "do_sample": true               },      "batch_size": 1,            // batch size for generate      "sample_num": 1,            // The number of samples generated by a single piece of data      "decode_mode": "beams"      // choose decode mode defined in generation_config    }  }

To check whether the reference values provided by the evaluation data set are correct,we provide the following command to check the dataset.

CodeCompletion

bash codefuseEval/script/check_dataset.sh humaneval_pythonbash codefuseEval/script/check_dataset.sh humaneval_javabash codefuseEval/script/check_dataset.sh humaneval_jsbash codefuseEval/script/check_dataset.sh humaneval_rustbash codefuseEval/script/check_dataset.sh humaneval_gobash codefuseEval/script/check_dataset.sh humaneval_cpp

NL2Code

bash codefuseEval/script/check_dataset.sh mbpp

CodeTrans

bash codefuseEval/script/check_dataset.sh codeTrans_python_to_javabash codefuseEval/script/check_dataset.sh codeTrans_python_to_cppbash codefuseEval/script/check_dataset.sh codeTrans_cpp_to_javabash codefuseEval/script/check_dataset.sh codeTrans_cpp_to_pythonbash codefuseEval/script/check_dataset.sh codeTrans_java_to_pythonbash codefuseEval/script/check_dataset.sh codeTrans_java_to_cpp

CodeScience

bash codefuseEval/script/check_dataset.sh codeCompletion_matplotlibbash codefuseEval/script/check_dataset.sh codeCompletion_numpybash codefuseEval/script/check_dataset.sh codeCompletion_pandasbash codefuseEval/script/check_dataset.sh codeCompletion_pytorchbash codefuseEval/script/check_dataset.sh codeCompletion_scipybash codefuseEval/script/check_dataset.sh codeCompletion_sklearnbash codefuseEval/script/check_dataset.sh codeCompletion_tensorflowbash codefuseEval/script/check_dataset.sh codeInsertion_matplotlibbash codefuseEval/script/check_dataset.sh codeInsertion_numpybash codefuseEval/script/check_dataset.sh codeInsertion_pandasbash codefuseEval/script/check_dataset.sh codeInsertion_pytorchbash codefuseEval/script/check_dataset.sh codeInsertion_scipybash codefuseEval/script/check_dataset.sh codeInsertion_sklearnbash codefuseEval/script/check_dataset.sh codeInsertion_tensorflow