Qiang's picture

4 33

Qiang

mikv39

·

null-define

AI & ML interests

None yet

Recent Activity

liked a model 4 days ago

MrDragonFox/mOrpheus_3B-1Base_early_preview

liked a model 5 days ago

dreamgen/lucid-v1-nemo

reacted to m-ric's post with 🚀 8 days ago

New king of open VLMs: InternVL3 takes Qwen 2.5's crown! 👑 InternVL have been a wildly successful series of model : and the latest iteration has just taken back their crown thanks to their superior, natively multimodal vision training pipeline. ➡️ Most of the vision language models (VLMs) these days are built like Frankenstein : take a good text-only Large Language Model (LLM) backbone, stitch a specific vision transformer (ViT) on top of it. Then the training is sequential 🔢 : 1. Freeze the LLM weights while you train the ViT only to work with the LLM part, then 2. Unfreeze all weights to train all weights in order to work together. 💫 The Shanghai Lab decided to challenge this paradigm and chose this approach that they call "native". For each of their model sizes, they still start from a good LLM (mostly Qwen-2.5 series, did I tell you I'm a huge fan of Qwen? ❤️), and stitch the ViT, but they don't freeze anything : they train all weights together with interleaved text and image understanding data in a single pre-training phase 🎨. They claim it results in more seamless interactions between modalities. And the results prove them right: they took the crown of top VLMs, at nearly all sizes, from their Qwen-2.5 parents. 👑

View all activity

Organizations

None yet

mikv39's activity

New activity in microsoft/Phi-4-multimodal-instruct about 2 months ago

Can we run inference without flash attention

#9 opened about 2 months ago by

New activity in ValueFX9507/Tifa-Deepsex-14b-CoT-GGUF-Q4 3 months ago

[Issue]生成文字时<think>缺失

#8 opened 3 months ago by

New activity in openbmb/MiniCPM-o-2_6 3 months ago

Could you share more information about the on device demo?

#11 opened 3 months ago by

New activity in upstage/solar-pro-preview-instruct 7 months ago

i tested the q8 in lm studio( getting wrong output)

#9 opened 7 months ago by