AI is happening. The future is updating.ruRoPEBert-e5-base-2k
This is an encoder model from **Tochka AI** based on the **RoPEBert** architecture, using the cloning method described in our article on Habr. CulturaX 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 and all other models in quality (at the time of creation), according to the `S+W` score of encodechka benchmark. The model is trained on contexts **up to 2048 tokens** in length, but can be used on larger contexts.
This is an encoder model from **Tochka AI** based on the **RoPEBert** architecture, using the cloning method described in our article on Habr. CulturaX 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 and all other models in quality (at the time of creation), according to the `S+W` score of encodechka benchmark. The model is trained on contexts **up to 2048 tokens** in length, but can be used on larger contexts.