Theodore Speak

theospeak

AI & ML interests

None yet

Recent Activity

liked a Space 3 months ago

webml-community/llama-3.2-webgpu

liked a Space 4 months ago

VIDraft/mouse1

liked a model 4 months ago

rhymes-ai/Allegro-TI2V

View all activity

Organizations

None yet

theospeak's activity

liked a Space 3 months ago

Llama 3.2 WebGPU

🦙

A powerful AI chatbot that runs locally in your browser

liked a Space 4 months ago

161

Mouse1 - WebApp Auto Creator AI

🦀

"One-minute creation by AI Coding Autonomous Agent MOUSE"

liked 3 models 4 months ago

liked a dataset 4 months ago

Skylion007/openwebtext

Updated May 17, 2024 • 86.8k • 400

liked a Space 4 months ago

1.42k

Qwen2.5 Coder Artifacts

🐢

Generate code from a description

liked a model 4 months ago

funasr/paraformer-en

Updated Feb 1, 2024 • 19 • 3

upvoted a paper 4 months ago

LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation

Paper • 2411.04997 • Published Nov 7, 2024 • 37

reacted to merve's post with 🔥 4 months ago

Post

1683

Microsoft released LLM2CLIP: a CLIP model with longer context window for complex text inputs 🤯
All models with Apache 2.0 license here microsoft/llm2clip-672323a266173cfa40b32d4c

TLDR; they replaced CLIP's text encoder with various LLMs fine-tuned on captioning, better top-k accuracy on retrieval.
This will enable better image-text retrieval, better zero-shot image classification, better vision language models 🔥
Read the paper to learn more: LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation (2411.04997)