Fill-Mask
Transformers
Safetensors
modernbert
masked-lm
long-context
timpal0l commited on
Commit
1ababe2
·
verified ·
1 Parent(s): 02bf196

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -19,6 +19,8 @@ base_model:
19
  ## Overview
20
  This checkpoint continues the pre-training of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on Scandinavian text, extending the model’s knowledge with ~1.2 trillion additional masked-language-model (MLM) tokens drawn from [The Nordic Pile](https://arxiv.org/pdf/2303.17183) and [SWEb](https://arxiv.org/pdf/2410.04456) while preserving the original 8k token context window.
21
 
 
 
22
  Our tokenizer is trained from scratch on a subset of 11 985 103 472 tokens.
23
 
24
  The training is done in one stage with 8192 tokens per sample for the whole run.
 
19
  ## Overview
20
  This checkpoint continues the pre-training of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on Scandinavian text, extending the model’s knowledge with ~1.2 trillion additional masked-language-model (MLM) tokens drawn from [The Nordic Pile](https://arxiv.org/pdf/2303.17183) and [SWEb](https://arxiv.org/pdf/2410.04456) while preserving the original 8k token context window.
21
 
22
+ This is a **research artefact** and is only intended for **research purposes**.
23
+
24
  Our tokenizer is trained from scratch on a subset of 11 985 103 472 tokens.
25
 
26
  The training is done in one stage with 8192 tokens per sample for the whole run.