# Bilingual Support

A compact language model based on the Llama architecture, supporting English and Portuguese, with 96 million parameters and a context length of 4096 tokens.

This is a BERT-based sentiment analysis model for Indonesian language, capable of classifying text into positive or negative sentiments.

An image classification model fine-tuned based on Facebook's DINOv2 base model, specifically designed for diabetic retinopathy detection, achieving 96.8% accuracy on the evaluation set.

Yehia is an empathetic Arabic language model, developed based on ALLaM-7B-Instruct-preview, offering considerate, friendly, and practical Arabic and English conversations.

A Chinese text chunking tool based on BertForTokenClassification, particularly suitable for processing unstructured and messy text

LLaVA-Saiga-8b is a vision-language model (VLM) developed based on the IlyaGusev/saiga_llama3_8b model, primarily optimized for Russian tasks while retaining English processing capabilities.

InternLM-Math-Plus is the state-of-the-art bilingual open-source mathematical reasoning large language model, equipped with solving, proving, verifying, and enhancing capabilities.

Llama 2 is an open-source large language model developed by Meta, supporting multiple languages including English and Arabic.

This is a 7B parameter large language model merged from Mistral-7B-Instruct-v0.1 and SauerkrautLM-7b-HerO, supporting English and German text generation tasks.

A German semantic textual similarity model fine-tuned based on multilingual-e5-base, optimized for multiple German datasets

An image classification model covering 22 most common tree diseases, containing over 290 image samples, usable for detecting tree health conditions.

This is a model for sentiment analysis of Korean text, capable of determining the emotional tendency (positive/negative) of the text.

A bilingual summarization model based on the multilingual T5 model, supporting German and English text summarization tasks