view post Post 5041 OmniVision-968M: a new local VLM for edge devices, fast & small but performantšØ a new vision language model with 9x less image tokens, super efficient š aligned with DPO for reducing hallucinationsā”ļø Apache 2.0 license š„Demo hf.co/spaces/NexaAIDev/omnivlm-dpo-demoModel https://huggingface.co/NexaAIDev/omnivision-968M 4 replies Ā· š„ 18 18 š 4 4 š¤ 2 2 + Reply
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF Text Generation ā¢ Updated Oct 25, 2024 ā¢ 280k ā¢ 1.96k