CohereLabs has released North-Micro-Vision-Instruct, a 2.4 billion parameter vision-language model under the Apache 2.0 license. This model features a SigLIP 2 Encoder, supports a 128K text context window and 8K multimodal context, and includes Flash Attention 2. Notably, it does not support tool calling or system prompts. AI
IMPACT Provides a new open-source vision-language model with a large context window for multimodal tasks.
RANK_REASON Release of an open-source model with specific technical details. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Mastodon — mastodon.social →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
