# Polish language generation

Bielik-4.5B-v3 is a Polish generative text model with 4.6 billion parameters, developed by SpeakLeash in collaboration with ACK Cyfronet AGH, trained on a curated Polish corpus.

This model is the FP8 quantized version of Bielik-4.5B-v3.0-Instruct, utilizing AutoFP8 technology to quantize weights and activations into FP8 data type, reducing approximately 50% of disk space and GPU memory requirements.

Bielik-4.5B-v3-Instruct is a 4.6 billion parameter Polish generative text model, fine-tuned based on Bielik-4.5B-v3, demonstrating exceptional Polish language comprehension and processing capabilities.

Bielik-11B-v2 is a generative text model with 11 billion parameters, specifically developed and trained for Polish language text. It is initialized based on Mistral-7B-v0.2 and trained on 400 billion tokens.

This is a 7B-parameter instruction fine-tuned model for Polish language, developed based on SpeakLeash's Bielik-7B-v0.1 model and quantized in GGUF format.