CodeRL
CodeRL copied to clipboard
salesforce
This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).
Bumps [transformers](https://github.com/huggingface/transformers) from 3.5.1 to 4.30.0. Release notes Sourced from transformers's releases. v4.30.0: 100k, Agents improvements, Safetensors core dependency, Swiftformer, Autoformer, MobileViTv2, timm-as-a-backbone 100k Transformers has just reached 100k stars...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [requests](https://github.com/psf/requests) from 2.22.0 to 2.31.0. Release notes Sourced from requests's releases. v2.31.0 2.31.0 (2023-05-22) Security Versions of Requests between v2.3.0 and v2.30.0 are vulnerable to potential forwarding of Proxy-Authorization...
Bumps [requests](https://github.com/psf/requests) from 2.22.0 to 2.31.0. Release notes Sourced from requests's releases. v2.31.0 2.31.0 (2023-05-22) Security Versions of Requests between v2.3.0 and v2.30.0 are vulnerable to potential forwarding of Proxy-Authorization...
@henryhungle This is a really nice work that is briging the gap between SE and AI! However, it seems incomplete yet. In the README, you said that "We will release...
Hi authors, can you add some documentation for the `test_one_solution.py` file please? I have 2 questions here - what does `test_one_solution.py` do? (what's the input and output?) - How to...
Hello, I noticed that you have trained a classification model (Critic). How did you overcome the problem of category imbalance in data? As far as I know, accepted solutions should...
Hi, I wonder what's the exact input formats for APPS/MBPP problems to be fed into [CodeT5-large-ntp-py](https://huggingface.co/Salesforce/codet5-large-ntp-py) or [CodeT5-finetuned_CodeRL](https://console.cloud.google.com/storage/browser/sfr-coderl-research/codet5_finetuned_codeRL)? I tried """{Problem}""" but it doesn't work well, generating a lot of...
I am reading your CodeRL paper. It uses the APPS benchmark to show the performance comparison with Codex. Do you have any comparison results using the HumanEval dataset?
start_idx variable in line `problem_idx += start_idx` is not defined in extract_example_test.ipynb
Metadata
Owner
Metadata
This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).