# Small Parameter Efficiency

OpenRS3-GRPO-ja is a fine-tuned version of the SakanaAI/TinySwallow-1.5B-Instruct model on a Japanese mathematical instruction dataset, trained using the GRPO method, focusing on mathematical reasoning tasks.

Qwen2-1.5B-Instruct is a 1.5 billion parameter instruction fine-tuned large language model released by Alibaba Cloud, suitable for Q&A and dialogue tasks.

Cuckoo is a small (300M parameters) information extraction model that efficiently extracts information by mimicking the next-word prediction paradigm of large language models

A vision-language model based on Microsoft's Phi-1.5 architecture, combined with CLIP for image processing capabilities

LLaVA model fine-tuned based on Phi-3-mini-4k-instruct and CLIP-ViT-Large-patch14-336, supporting image-to-text tasks

A large language model fine-tuned on the ultrachat_200k dataset based on microsoft/phi-2, suitable for dialogue generation tasks.

This is a model based on the Open Llama 3B V2 architecture, trained using the WizardLM_evol_instruct_V2_196k dataset, suitable for instruction-following tasks.

LaMini-T5-61M is an instruction-following model based on the T5-small architecture, fine-tuned on the LaMini-instruction dataset with a parameter scale of 61M.