Image created with OpenAI GPT-Image-1. Image prompt: vintage Sly & the Family Stone album-cover style, bold rainbow typography bursting from center, dancing silhouettes featuring stylized llama wearing VR goggles; grainy retro print texture, vibrant 60s funk color palette, high-resolution
Pretty impressive 7B VLM coming out of Xiaomi 🤓 ViT encoder w/ MLP and powered by their 7B Text backbone Compatible w/ Qwen VL arch so works across vLLM, Transformers, SGLang and Llama.cpp Bonus: it can reason and is MIT licensed 🔥 https://x.com/reach_vb/status/1928360066467439012
Ollama can now think! 🤔🤔🤔 For thinking models, and especially useful for very thoughtful models like DeepSeek-R1-0528, Ollama can separate the thoughts and the response. Thinking can also be disabled! This is useful for getting a direct response. This works across https://x.com/ollama/status/1928543644090249565
⚠️⚠️⚠️Qwen team has worked on training pivot tokens ⚠️⚠️⚠️ @_xjdr @doomslide amusingly, they *do* test it on Llama 3.1 as well but find it so ass that no conclusive results can be had without cold start with Qwen data https://x.com/i/web/status/1929755590404055358
