Polanka 7b - Polish LLM based on Mistral
Warning, this is still work in progress.
First version of 7b Polish LLM finetuned using custom data in Polish language.
As a base model I used uncensored https://huggingface.co/ehartford/dolphin-2.1-mistral-7b so Dolphin "personality" should also be there.
It was trained on 4K context in ChatML format.
- Downloads last month
- 1,499
Inference API (serverless) is not available, repository is disabled.