Skip to content Skip to sidebar Skip to footer
AI News

startups: India pushes technology, fintech & startup partnership with Philippines

India through its Embassy in Philippines on Tuesday launched the first India-Philippine Tech Summit (IPTS) to help boost tech and digital partnership with Manila.In his speech during the IPTS in Taguig City, Indian Ambassador to Manila Shambhu Kumaran referred to the need for developing countries to develop partnerships amongst themselves —particularly in security, people-to-people ties,…
March 7, 20240Likes0Comments
AI News

Google Bard AI now chats in 40 languages including Hindi, supports image prompts and expands to new regions

Google has announced a significant update for Bard, its formidable competitor to ChatGPT. The latest update brings exciting features, including multilingual support in 40 languages, with a particular emphasis on catering to the diverse linguistic needs of users in India. Bard can now fluently communicate in Hindi, Tamil, Telugu, Bengali, Kannada, Malayalam, Marathi, Gujarati, and Urdu.…
March 7, 20240Likes0Comments
Text Classification

XLMRoberta-Alexa-Intents-Classification

People Involved LABRAK Yanis (1) Affiliations LIA, NLP team, Avignon University, Avignon, France. Demo: How to use in HuggingFace Transformers Pipeline Requires transformers: pip install transformers from transformers import AutoTokenizer, AutoModelForSequenceClassification, TextClassificationPipeline model_name = 'qanastek/XLMRoberta-Alexa-Intents-Classification' tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForSequenceClassification.from_pretrained(model_name) classifier = TextClassificationPipeline(model=model, tokenizer=tokenizer) res = classifier("réveille-moi à neuf heures du matin le vendredi"…
March 7, 20240Likes0Comments
VLLMs

llava-v1.6-mistral-7b-PATCHED

LLaVA Model Card - PATCHED! This is a patched version of the original model, with patches from aliencaocao applied from here. Model details Model type: LLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: mistralai/Mistral-7B-Instruct-v0.2 Model date: LLaVA-v1.6-Mistral-7B was…
March 7, 20240Likes0Comments
Visual Question Answering

pix2struct-ocrvqa-large

Model card for Pix2Struct - Finetuned on OCR-VQA (Visual Question Answering over book covers) - large version Table of Contents TL;DR Using the model Contribution Citation TL;DR Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and…
March 7, 20240Likes0Comments