muyihenhen
/

twitch-roberta-base

domain-adaptation

masked-language-modeling

Model card Files Files and versions

muyihenhen commited on Dec 13, 2025

Commit

c97b90b

·

verified ·

1 Parent(s): d495546

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ It solves the "Domain Shift" problem where standard NLP models (trained on Wikip
 ## Model Performance
 | Metric | Baseline (Twitter-RoBERTa) | **Twitch-RoBERTa (This Model)** |
 | :--- | :--- | :--- |
-| **Perplexity** | ~134 | **~5.5** |
 | **Loss** | 9.97 | **1.7** |
 **Result:** A **~82% reduction in perplexity**, effectively teaching the model the specific vocabulary, syntax, and emote usage patterns of the Twitch community.

 ## Model Performance
 | Metric | Baseline (Twitter-RoBERTa) | **Twitch-RoBERTa (This Model)** |
 | :--- | :--- | :--- |
+| **Perplexity** | ~21,375 | **~5.5** |
 | **Loss** | 9.97 | **1.7** |
 **Result:** A **~82% reduction in perplexity**, effectively teaching the model the specific vocabulary, syntax, and emote usage patterns of the Twitch community.