Hailay
/

xlmr-amharic-mlm

masked-language-modeling

Model card Files Files and versions

Hailay commited on Jul 15, 2025

Commit

f7b63bf

·

verified ·

1 Parent(s): e878f53

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ This model is a fine-tuned version of [`xlm-roberta-base`](https://huggingface.c
 - **Base model**: `xlm-roberta-base`
 - **Language**: Amharic
-- **Tokenizer**: Custom BPE tokenizer (not morpheme-aware)
 - **Adaptation**: Embedding initialization via weighted average of pretrained XLM-R embeddings, guided by FastText word vectors for Amharic
 - **Training dataset**: Amharic portion of the [NLLB (No Language Left Behind)](https://github.com/facebookresearch/flores) parallel corpus
 - **Objective**: Masked Language Modeling (MLM)

 - **Base model**: `xlm-roberta-base`
 - **Language**: Amharic
+- **Tokenizer**: Custom BPE tokenizer
 - **Adaptation**: Embedding initialization via weighted average of pretrained XLM-R embeddings, guided by FastText word vectors for Amharic
 - **Training dataset**: Amharic portion of the [NLLB (No Language Left Behind)](https://github.com/facebookresearch/flores) parallel corpus
 - **Objective**: Masked Language Modeling (MLM)