Leshem Choshen

Feature request: user responses

2

Hi, I think this is the most robust portal for our field I have ever seen, kudos. How hard for you will it be to add either or both of...

unable to parse

11

hello, I have been trying to install and use treat, but when I try parsing, I get the following error: irb(main):008:0> s = sentence('this is another test').parse LoadError: cannot load...

Trained models

1

Is it possible to upload the models and perhaps have a documentation on how to correct using the trained models (whether supplied or not)

Hi, Could you add a license to this project? (If you want the most permissive, you probably look for MIT license)

The leaderboard is down

1

I tried today and last week, and the leaderboard is not loading: 

improved readability and creates needed directories automatically

Hey, Do you have the train\eval loss\ performance during training (I see the checkpoints ones, but wondered if you also had more frequently sampled data throughout training). Thanks

Training code

1

### 📚 The doc issue In the release there is a link to "training code" but it just leads to the github that doesn't document how can one reproduce training...

With current trends, should we move from GEC and MT to look for progress on larger kinds of abilities? Instruction following (tuning) Learning from context (In context learning) etc.

In your blog you bring many runs and iterations and scaling laws. Could you share the training losses and parameters from which those graphs are made for further research and...