usmiva
/

bert-web-bg

feature-extraction

Generated from Trainer

Model card Files Files and versions

usmiva commited on Jul 26, 2023

Commit

2d65dd8

·

1 Parent(s): 99bfde6

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -4,7 +4,7 @@ tags:
 metrics:
 - accuracy
 model-index:
-- name: bg-news-bert
   results: []
 license: cc-by-2.0
 language:
@@ -15,9 +15,9 @@ pipeline_tag: fill-mask
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
-# bg-news-bert
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the [BG-WEB dataset](https://huggingface.co/datasets/identrics/bg_web).
 It achieves the following results on the evaluation set:
 - Loss: 1.4510
 - Accuracy: 0.6906

 metrics:
 - accuracy
 model-index:
+- name: bert-web-bg
   results: []
 license: cc-by-2.0
 language:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
+# bert-web-bg
+This model is pretrained from scratch BERT on Bulgarian dataset created at the Bulgarian Academy of Sciences under the [ClaDa-BG Project](https://clada-bg.eu/en/) .
 It achieves the following results on the evaluation set:
 - Loss: 1.4510
 - Accuracy: 0.6906