23 98 91

Andrew Reed

andrewrreed

https://www.andrewreed.com

AI & ML interests

Applied ML, Practical AI, Inference & Deployment, LLMs, Multi-modal Models, RAG

Recent Activity

upvoted an article 1 day ago

Dell Enterprise Hub is all you need to build AI on premises

published an article 12 days ago

Dell Enterprise Hub is all you need to build AI on premises

liked a Space 29 days ago

smolagents/computer-agent

View all activity

Organizations

andrewrreed's activity

upvoted an article 1 day ago

Article

Dell Enterprise Hub is all you need to build AI on premises

and 7 others •

12 days ago

• 18

published an article 12 days ago

Article

Dell Enterprise Hub is all you need to build AI on premises

and 7 others •

12 days ago

• 18

liked a Space 29 days ago

830

Computer Agent

🖥

Interact with an agent to perform web-based tasks

commented on How to Build an MCP Server with Gradio about 1 month ago

V excited about this!

upvoted an article about 1 month ago

Article

How to Build an MCP Server with Gradio

and 1 other •

Apr 30

• 147

liked a Space about 1 month ago

659

Open Deep-Research

🏆

OpenAI's Deep Research, but open

upvoted 2 articles about 1 month ago

Article

Tiny Agents: a MCP-powered agent in 50 lines of code

•

Apr 25

• 267

Article

17 Reasons Why Gradio Isn't Just Another UI Library

and 1 other •

Apr 16

• 37

New activity in deepseek-ai/DeepSeek-R1 about 1 month ago

Remove "NOTE: Hugging Face's Transformers has not been directly supported yet." in README

#216 opened about 1 month ago by

andrewrreed

upvoted 2 articles about 1 month ago

Article

An Introduction to AI Model Optimization Techniques

and 1 other •

Apr 18

• 28

Article

Gotchas in Tokenizer Behavior Every Developer Should Know

•

Apr 18

• 37

upvoted an article about 2 months ago

Article

Cohere on Hugging Face Inference Providers 🔥

and 6 others •

Apr 16

• 126

upvoted a collection about 2 months ago

Kimi-VL-A3B

Collection

Moonshot's efficient MoE VLMs, exceptional on agent, long-context, and thinking • 6 items • Updated Apr 12 • 65

liked a Space about 2 months ago

Repo Graph

👁

A byte-level map of the Hugging Face Hub

reacted to jsulz's post with 🔥 about 2 months ago

Post

3766

Huge week for

xet-team as Llama 4 is the first major model on Hugging Face uploaded with Xet providing the backing! Every byte downloaded comes through our infrastructure.

Using Xet on Hugging Face is the fastest way to download and iterate on open source models and we've proved it with Llama 4 giving a boost of ~25% across all models.

We expect builders on the Hub to see even more improvements, helping power innovation across the community.

With the models on our infrastructure, we can peer in and see how well our dedupe performs across the Llama 4 family. On average, we're seeing ~25% dedupe, providing huge savings to the community who iterate on these state-of-the-art models. The attached image shows a few selected models and how they perform on Xet.

Thanks to the