Back

Roast if you can! Evanth AI (www.evanth.in) We offer all top LLMs at just 99₹ and upto an unlimited like experience. No rate limitations and no hidden fees. Web Search Integrated Which model? OpenAI, Mistral, Hugging Face, DeepSeek, Perplexity, Ll

Welcome to on-device Al: Google just dropped an official open-source app for running an Al model locally on a phone Imagine running a powerful Ai - No Internet, No cloud, No lag - right from your phone 📱 Now you can! Google just dropped Al Edge G

Google Unveils AI Edge Gallery: On-Device Generative AI Without Internet Google has launched the AI Edge Gallery, an experimental app that brings cutting-edge Generative AI models directly to your Android device. Once a model is downloaded, all proc

"Just fine-tuned LLaMA 3.2 using Apple's MLX framework and it was a breeze! The speed and simplicity were unmatched. Here's the LoRA command I used to kick off training: ``` python lora.py \ --train \ --model 'mistralai/Mistral-7B-Instruct-v0.2' \ -

Cool stuffs happening 🙌. OpenAI's shift toward open models has hit a new landmark. You can now download two open-weight reasoning models, similar to its o-series, right now on the developer platform Hugging Face. OpenAI hasn't actually launched an

Want to learn AI the right way in 2025? Don’t just take courses. Don’t just build toy projects. Look at what’s actually being used in the real world. The most practical way to really learn AI today is to follow the models that are shaping the indus

Hello everyone! 👋 This is my first post here I’m excited to introduce Navagni, the no-code AI fine-tuning platform from Navdyut AI. Just bring your data (drag-and-drop, any format), pick a model (like Llama or Mistral), and Navagni automatically fin

Day 23 of learning python as a beginner. Topic: multi-threading. Multi-threading is a technique to run multiple task (such as importing or downloading) within a single program and at the same time. Thus running multiple things parallelly, in a nuts

We just crossed 4,188+ users. But truth? That’s not the headline. Two of our core engineers left. They were good — they built with me. But when vision doesn’t align, you part ways. Not with anger. With clarity. Because this road needs more than tale

AGI is a scam We will never reach AGI with LLM models A Large language model is train on 1 trillion tokens A token is like a word 10 to the power 14 that is 1 behind 14 zeors (100000000000000) this is all available text on internet It will