Edit model card

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
1,437
Safetensors
Model size
7.24B params
Tensor type
F32
FP16
I8
Inference Examples
Inference API (serverless) is not available, repository is disabled.