# For Academic Research

OLMo 2 1B SFT is a supervised fine-tuned version of the OLMo-2-0425-1B model, trained on the Tulu 3 dataset, designed to achieve state-of-the-art performance across multiple tasks.

LlavaGuard is a safety evaluation guardian based on vision-language models, primarily used for safety classification and violation detection of image content.

LlavaGuard is a vision-language model-based safety assessment system for security classification and compliance checking of image content.

This is a pre-trained time series forecasting model, focusing on time series data analysis and prediction tasks.

Cambrian is an open-source multimodal LLM (Large Language Model) designed with a vision-centric approach.

CLIP model based on ViT-L/14 and masked self-attention Transformer for zero-shot image classification research

A supervised fine-tuned model based on LLaMA-3-8B, developed by Salesforce, for the supervised fine-tuning phase in reinforcement learning from human feedback (RLHF) workflows.

LLaMAntino-3-ANITA is a multilingual (English + Italian) large language model based on Meta Llama 3, specifically optimized for Italian NLP tasks.

LLaMA-7B is an efficient foundational language model developed by Meta AI, based on the Transformer architecture with 7 billion parameters, suitable for natural language processing research.

LLaVA is an open-source chatbot fine-tuned with GPT-generated multimodal instruction-following data based on LLaMA/Vicuna

LLaVA is an open-source chatbot fine-tuned with GPT-generated multimodal instruction-following data based on LLaMA/Vicuna, supporting visual and language multimodal interactions.

LLaMA is an efficient foundational language model developed by Meta AI, available in parameter sizes ranging from 7B to 65B. Based on the Transformer architecture, it is suitable for various natural language processing tasks.

A RoBERTa-base based model for detecting ChatGPT-generated text, distinguishing between human-written and ChatGPT-generated content

This is a pre-trained language model specifically for Nepali, with research results published in the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (2022).

GerPT2 is the large-scale version of the German GPT2, trained on the CC-100 corpus and German Wikipedia, excelling in German text generation tasks.

Arabic pre-trained language model based on BERT architecture, supporting masked language modeling tasks