Hugging Face's logo

AhmetSemih
/
llama_50m_pretrained_news_tr_tokenizer

Turkish
Model card Files
xet
 Community
AhmetSemih commited on
Commit
ba9f20b
·
verified ·
1 Parent(s): 2de55df

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -31,7 +31,7 @@ language:
31
 
32
  ## Model Description
33
 
34
- `llama-50m-turkish-books` is a **50 million parameter Turkish language model** trained from scratch on the `habanoz/news-tr-1.8M` dataset.
35
  It was developed as a lightweight experimental model to explore **Turkish-specific tokenization and morphology-aware pretraining** using the custom [turkish_tokenizer](https://github.com/malibayram/turkish-tokenizer).
36
 
37
  The model follows the **LLaMA-style causal transformer** architecture and was trained with a context length of 256 tokens over ~372M tokens in total.
 
31
 
32
  ## Model Description
33
 
34
+ `llama_50m_tr_tokenizer_news` is a **50 million parameter Turkish language model** trained from scratch on the `habanoz/news-tr-1.8M` dataset.
35
  It was developed as a lightweight experimental model to explore **Turkish-specific tokenization and morphology-aware pretraining** using the custom [turkish_tokenizer](https://github.com/malibayram/turkish-tokenizer).
36
 
37
  The model follows the **LLaMA-style causal transformer** architecture and was trained with a context length of 256 tokens over ~372M tokens in total.