Omnivision-968M: Vision Language Model with 9x Tokens Reduction for Edge Devices (nexa.ai) | HN Screenshots

YHacker Newsscreenshots

Screenshot of nexa.ai: Omnivision-968M: Vision Language Model with 9x Tokens Reduction for Edge Devices

First screen, captured 1 year ago.

Looks similar

Screenshot of microsoft.github.io: OmniParser for Pure Vision Based GUI Agent

OmniParser for Pure Vision Based GUI Agent (microsoft.github.io)

137 points by fzliu 2 years ago | 29 comments

Screenshot of xy2i.blogspot.com: Visualizing binary files with ImHex's DSL, the "pattern language"

Visualizing binary files with ImHex's DSL, the "pattern language"(xy2i.blogspot.com)

167 points by xy2_ 1 year ago | 15 comments

Screenshot of gab-menezes.github.io: Using the most unhinged AVX-512 instruction to make fastest phrase search algo

Using the most unhinged AVX-512 instruction to make fastest phrase search algo (gab-menezes.github.io)

207 points by cmcollier 1 year ago | 54 comments

Screenshot of stateofutopia.com: MicroLLM Lab – Try 7 tiny LLM's in the browser

MicroLLM Lab – Try 7 tiny LLM's in the browser (stateofutopia.com)

271 points by logicallee 28 days ago | 99 comments

MicroLLM Lab is a browser-based tool for running, chatting with, and benchmarking small quantized language models locally via WebGPU with no server.

small-language-models webgpu in-browser-inference quantization

Screenshot of rwkv.com: RWKV Language Model

RWKV Language Model (rwkv.com)

147 points by simonpure 1 year ago | 47 comments

Screenshot of Hacker News post: Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model

Show HN: Emu2 – A Gemini-like open-source 37B Multimodal Model

120 points by BAAIBeijing 2 years ago | 14 comments