“You can build a full-stack application using Python. No JavaScript, CSS, or HTML. Here is an open-source Python library to build end-to-end production applications:
Hugging Face
“Open-source AI creates healthy competition in a field where natural tendencies lead to extreme concentration of power. Imagine a world where only one or two companies could build software. This is the biggest risk and ethical challenge of them all IMO. Let’s fight this!
“How can you efficiently serve open LLMs from @huggingface on @Google TPUs? Hex-LLM is a new LLM serving framework designed for TPUs, offering low-cost, high-throughput deployment for open models from Hugging Face. 👀 TL;DR: 🚀 Token-based continuous batching, XLA-optimized
rhymes-ai (Rhymes.AI)
FacePoke – a Hugging Face Space by jbilcke-hf
rain1011/pyramid-flow-sd3 · Hugging Face
“Try Flux Schnell for free in this @huggingface space! This model is free in the Together API for the next 3 months.
Video Background Removal – a Hugging Face Space by innova-ai
“man, the huggingface team is *cracked* two days after i released my contextual embedding model, which has a pretty different API, @tomaarsen implemented CDE in sentence transformers you can already use it implementation was not at all trivial; those people just work fast
Welcome, Gradio 5
Meta/Llama
How Neuromnia is transforming ABA therapy with Llama 3.1
“LLMs are undergoing progressive commoditization. For simple tasks, we’re already at OSS dominance. There’s nothing closed-source that’s both cheaper and better than Llama 3.2 3B. This will likely extend to larger model sizes over time.” / X
“Introducing Multimodal Llama 3.2, made in collaboration with @AIatMeta and taught by @asangani7, is live! Explore the latest features in @Meta’s Llama 3.2, from custom tool-calling to multimodal capabilities and the Llama Stack. Enroll for free 👇
“Previously, RAG systems were the standard method for retrieving information from documents. However, if you are not repeatedly querying the same document, it may be more convenient and effective to just use long-context LLMs. For example, Llama 3.1 8B and Llama 3.2 1B/3B now
Reka
“We have been busy the past few months and have some exciting updates!📢 We have a new version of Reka Flash⚡️, our powerful 21B model that supports interleaved multimodal inputs (text📄, image🖼️, video📽️, audio🎧). This update brings significant capability improvements on https://twitter.com/RekaAILabs/status/1843298155682820566
Leave a Reply