We make the codes publicly available – open source.
Hello! Today we will describe the technical aspects. Over the past month, we have been working on publishing some of our solutions. Today we would like to present a few …
Information Explorer- not a hammer, but a scalpel
Today’s blog post will be short, but the attachment is quite long 🙂 Intro i Outro We encourage you to take a look behind the scenes at how the Information …
3c Polarization – model from plg on HF
Hello 😉 Today, we are presenting and publishing an element of the playground’s. It is a classification model whose task is to determine the polarity of texts. We are publishing …
pLlama3.2 (1B + 3B) – małe GenAI dla polskiego
pLLama – wygenerowane za pomocą AI Intro Cześć Wam! Dziś bardzo krótki wpis. Wpis o modelu, niewielkim jak na te czasy. Pewnie słyszeliście o LLamie3.2 od MetaAI? Meta udostępniła ostatnio …
pLlama3 (8B + 70B) – GenAI dla polskiego
pLLama – wygenerowane za pomocą AI Intro Witajcie! W ostatnim wpisie wspominaliśmy o modelu GenaAI… Tak! Dzisiaj chcemy przedstawić Wam nasz nowy model, a właściwie to rodzinę modeli douczoną na …
RAG (problems?)
Today’s post will be a little different than usual. This time, we are not presenting a new model, but a description of the RAG method. The method is widely known, …
Bi-encoder and cross-encoder model
The possibilities offered by generative models are enormous, as evidenced by the success of OpenAI and its flagship product, ChatGPT. Generative models based on transformer architecture are on par with …
Text denoiser
Currently, the world of natural language processing is dominated by solutions based on transformer architecture models. The diversity of these models has practically dominated every area of NLP. Regardless of …
Extraction QA – our model polish-qa-v2
In the field of natural language processing, innovative solutions are constantly emerging that enable precise answers to questions in different languages. We present the polish-qa-v2 model, which represents a step …
Nowe modele gpt2!
Dzisiaj udostępniliśmy dwa modele gpt2 trenowane od podstaw. Jeden w architekturze small, drugi w medium. Modele oczywiście dostępne są publicznie na naszym huggingface 😉 Poniżej po dwa zrzuty ekranu z …