# Academic Research Only

A PyTorch-based pretrained model for time series forecasting, suitable for various time series data analysis tasks

The CNER model is a named entity recognition model based on the DeBERTa-v3-base architecture, capable of jointly identifying and classifying concepts and named entities with fine-grained labels.

LLaVA is an open-source multimodal chatbot trained by fine-tuning LLM on multimodal instruction-following data. This version is the GGUF quantized version, offering multiple quantization options.

TURNA is a Turkish language model based on the UL2 framework, suitable for comprehension and generation tasks, demonstrating excellent performance in multiple Turkish language tasks.

A physics-domain QA model based on the Phi-2 architecture, specifically fine-tuned for arXiv physics paper content

LLaVA-Plus is a pluggable learning skill-based large language and vision assistant, primarily used for academic research in multimodal models and chatbots.

LLaVA is an open-source multimodal chatbot, fine-tuned from LLaMA/Vicuna and trained on GPT-generated multimodal instruction-following data.

AraBERTMo is an Arabic pre-trained language model based on Google's BERT architecture, supporting fill-mask tasks.