SmolVLM

SmolLM2 is a collection of state-of-the-art, compact language models developed for on-device applications. The models in this collection range from 1.7B parameters to smaller 360M and 135M versions, designed to perform efficiently even on less powerful hardware. These models excel in text generation tasks and are optimized for real-time, low-latency applications, providing high-quality results across various use cases, including content creation, coding assistance, and natural language processing. SmolLM2's flexibility makes it a suitable choice for developers looking to integrate powerful AI into mobile devices, edge computing, and other resource-constrained environments.

LLaVA (Large Language-and-Vision Assistant) is an innovative multimodal model that integrates a vision encoder with the Vicuna language model to facilitate comprehensive visual and language understanding. Through end-to-end training, LLaVA exhibits impressive chat capabilities, emulating the multimodal functionalities of models like GPT-4. Notably, LLaVA-1.5 has achieved state-of-the-art performance across 11 benchmarks, utilizing publicly available data and completing training in approximately one day on a single 8-A100 node, surpassing methods that rely on billion-scale datasets. The development of LLaVA involved the creation of a multimodal instruction-following dataset, generated using language-only GPT-4. This dataset comprises 158,000 unique language-image instruction-following samples, including conversations, detailed descriptions, and complex reasoning tasks. This data has been instrumental in training LLaVA to perform a wide array of visual and language tasks effectively.