--- license: cc-by-sa-4.0 language: - pl --- # Model Card for Krakowiak-v2-7b Krakowiak-v2-7b is a state of the art 7.3 billion parameters LLM based on Mistral-7B. It was finetuned for Polish text generation using custom created large corpus of 100K Polish instructions. It uses novel techniques e.g. LORA, adding noise to the embeddings for great preformance. For full details of this model please read our [paper to be released soon](www.example.come) ## Model Architecture Krakowiak-v2-7b is a huge update to [Krakowiak-7b](https://huggingface.co/szymonrucinski/krakowiak-7b) bringing the following improvements: - Grouped-Query Attention - Sliding-Window Attention - Byte-fallback BPE tokenizer - Significantly larger training corpus of better quality - Improved training pipeline - Faster inference - No random token generation (generating Russian or Czech text alongside Polish) - Significantly higher quality of generated text Mistral 7B is a pretrained base model and therefore does not have any moderation mechanisms. ## Instruction format In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id. E.g. ``` text = "[INST] Czy warto się uczyć? [/INST]" "Jako model języka AI nie mam osobistych opinii ani przekonań. Jednak uczanie się jest ogólnie cenione i angażuje długoterminowe korzyści dla jednostki i społeczeństwa. Dzięki nauce można opracować umiejętności, zdobąć wiedzę i zwiększyć potencjał osobisty i zawodowy. Ponadto nauka promuje otwartość na innowacje i może zapewnić lepszą perspektywę życia. Dlatego uczanie się jest ogólnie cenione i wartościowe dla osób, które chcą osiągnąć cel lub rozwinąć swoją wiedzę. Jednak każda sytuacja może być inna i niektóre osoby mogą mieć różne cele lub okoliczności, które wpływają na ich podejście do nauki. Ostatecznie zależy to od indywidualnych preferencji i celów. " "[INST] Gdzie warto się uczyć? [/INST]" ``` ## Model parameters From my experience the temperature value of 0.7 is the best baseline value. ## Use a pipeline as a high-level helper ``` from transformers import pipeline pipe = pipeline("text-generation", model="szymonrucinski/krakowiak-v2-7b") pipe("[INST] Czy warto się uczyć? [/INST]") ``` ## Krakowiak team [Szymon Franciszek Ruciński](https://szymonrucinski.pl)