@epfml/discojs 2.1.2-p20240723160606.0 → 2.1.2-p20240724132346.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -9,7 +9,13 @@ export const wikitext = {
|
|
|
9
9
|
preview: 'Train a language model (L)LM in your browser, collaboratively and from scratch.',
|
|
10
10
|
overview: "You can train a GPT-2 model in your browser and in a collaborative manner on any textual dataset. As an example, you can try the Wikitext-103 dataset, composed of Wikipedia articles, widely used in natural language modeling, which you can download <a class='underline text-blue-400' target='_blank' href='https://dax-cdn.cdn.appdomain.cloud/dax-wikitext-103/1.0.1/wikitext-103.tar.gz'>here</a>. More information on how to connect the dataset at the next step."
|
|
11
11
|
},
|
|
12
|
-
model:
|
|
12
|
+
model: [
|
|
13
|
+
"The model follows the exact GPT-2 architecture and is implemented in TensorFlow.js.",
|
|
14
|
+
"The tokenizer used for preprocessing is the GPT-2 Byte-Pair encoding tokenizer.",
|
|
15
|
+
"The model is trained via an Adam optimizer with unit gradient clipping and softmax cross-entropy loss.",
|
|
16
|
+
"It has around 5M parameters.",
|
|
17
|
+
"To accommodate all devices, the context length is currently kept at 128 and the batch size at 1.",
|
|
18
|
+
].join(" "),
|
|
13
19
|
dataFormatInformation: 'You can use any natural language (text) dataset you like. For example the Wikitext-103 dataset is organized as a large text file, with each line representing a segment of raw text from Wikipedia articles.',
|
|
14
20
|
dataExampleText: 'An example excerpt from the dataset is: <i>"For the first twenty years of its existence , the only staged performances of Parsifal took place in the Bayreuth Festspielhaus , the venue for which Wagner conceived the work ( except eight private performances for Ludwig II at Munich in 1884 and 1885 ) ."</i>',
|
|
15
21
|
sampleDatasetLink: 'https://dax-cdn.cdn.appdomain.cloud/dax-wikitext-103/1.0.1/wikitext-103.tar.gz',
|