Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ This is an encoder model from **Tochka AI** based on the **RoPEBert** architectu
|
|
| 13 |
|
| 14 |
[CulturaX](https://huggingface.co/papers/2309.09400) dataset was used for model training. The **hivaze/ru-e5-base** (only english and russian embeddings of **intfloat/multilingual-e5-base**) model was used as the original; this model surpasses it in quality, according to the `S+W` score of [encodechka](https://github.com/avidale/encodechka) benchmark.
|
| 15 |
|
| 16 |
-
The model source code is available in the file [modeling_rope_bert.py](https://huggingface.co/Tochka-AI/ruRoPEBert-
|
| 17 |
|
| 18 |
The model is trained on contexts **up to 512 tokens** in length, but can be used on larger contexts. For better quality, use the version of this model with extended context - [Tochka-AI/ruRoPEBert-e5-base-2k](https://huggingface.co/Tochka-AI/ruRoPEBert-e5-base-2k)
|
| 19 |
|
|
|
|
| 13 |
|
| 14 |
[CulturaX](https://huggingface.co/papers/2309.09400) dataset was used for model training. The **hivaze/ru-e5-base** (only english and russian embeddings of **intfloat/multilingual-e5-base**) model was used as the original; this model surpasses it in quality, according to the `S+W` score of [encodechka](https://github.com/avidale/encodechka) benchmark.
|
| 15 |
|
| 16 |
+
The model source code is available in the file [modeling_rope_bert.py](https://huggingface.co/Tochka-AI/ruRoPEBert-e5-base-512/blob/main/modeling_rope_bert.py)
|
| 17 |
|
| 18 |
The model is trained on contexts **up to 512 tokens** in length, but can be used on larger contexts. For better quality, use the version of this model with extended context - [Tochka-AI/ruRoPEBert-e5-base-2k](https://huggingface.co/Tochka-AI/ruRoPEBert-e5-base-2k)
|
| 19 |
|