From 43f7a7e7424ec328c1d6dd3a948db7699f0571e6 Mon Sep 17 00:00:00 2001 From: Chris Waterson Date: Wed, 9 Mar 2016 10:50:15 -0800 Subject: [PATCH] Fix tables. --- swivel/README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/swivel/README.md b/swivel/README.md index 97a21318bc3..fff8cc6f431 100644 --- a/swivel/README.md +++ b/swivel/README.md @@ -88,6 +88,7 @@ By default, `prep.py` will make one pass through the text file to compute a co-occurrence statistics. The following options allow you to control this behavior: +| Option | Description | |:--- |:--- | | `--min_count ` | Only include words in the generated vocabulary that appear at least *n* times. | | `--max_vocab ` | Admit at most *n* words into the vocabulary. | @@ -115,6 +116,7 @@ that the Swivel trainer needs to run. Train embeddings as follows: There are a variety of parameters that you can fiddle with to customize the embeddings; some that you may want to experiment with include: +| Option | Description | |:--- |:--- | | `--embedding_size ` | The dimensionality of the embeddings that are created. By default, 300 dimensional embeddings are created. | | `--num_epochs ` | The number of iterations through the data that are performed. By default, 40 epochs are trained. |