nl2bash
nl2bash copied to clipboard
TellinaTool
Generating bash command from natural language https://arxiv.org/abs/1802.08979
Hello, I'm trying to reproduce the paper results, but I get an assertion error after few epochs while running "make train". Do you have any suggestion? Thanks! ``` Example 700...
Dear professor: I'm sorry to disturb you, I met a problem in make train, the problem is as follows: Traceback (most recent call last): File "/home/admin318/anaconda3/lib/python3.8/runpy.py", line 194, in _run_module_as_main...
I'm trying to do a smoke test for your eval suite but cannot get the script to run properly. I've followed the setup instructions: 1. run `make` in the root...
I am currently building a project that performs almost the same functions provided by this one, so I would like to know its top-level entry point works so that I...
Hi, I am tinkering with formalizing the semantics of shell commands for use with a planner. It occurred to me that NL2Bash, when run in the opposite direction, might help...
When looking at the results of `make data` in a clean repo clone, it seems there is a small overlap in NL descriptions of the train and test datasets (same...
I'd like to use pre-defined NN, how can I convert `Find all files in your home directory and below that are exactly 100M.` to the `find ~ -size 100m`? I...
Hi sir, I think your code is very meaningful and I want to reproduce it, but I have a problem and want to trouble you. When I was training, I...
A fresh git clone pulls in 1.1GBs, whereas the working directory is only close to 120MB. Please consider stripping down the repository size.
Metadata
Owner
Metadata
Generating bash command from natural language https://arxiv.org/abs/1802.08979