Sublime
An inspiration engine for ideas
QwQ-32B model from Qwen in VSCode... Got 20GB of free space? π
This is the latest reasoning model developed by @Alibaba_Qwen
In this video, I walk you through how to download and install it in VSCode using @ollama, completely free and private π https://t.co/BklcfLmnfk
Daniel Sanx.com
π¨ JAILBREAK ALERT π¨
OPENAI: PWNED βοΈπ
O1: LIBERATED βοΈβπ₯
Did not expect this todayβfull o1 was accessible for a brief window! At time of writing it's not working for me anymore, but when setting "model=o1" in the URL, the interface showed "ChatGPT" for the model name in the top... See more
Gemma 3 270M fine-tune on Windows with @UnslothAI. It worked! π₯³ https://t.co/SKfy9KJvjb
I made a Sora MCP π¬
The server can generate, remix, check video status, and even download videos to a folder of your choice
Repo on GitHub π https://t.co/XmWCXsXP2g
Pietro Schiranox.comHere are ten 42M TinyStories models running simultaneously in the browser. @karpathy's Llama2.c code has been ported to Rust using the Candle framework and compiled to Wasm. https://t.co/IK71azQMKU
RadamΓ©s Ajnax.com
Llama4 + MCP find me an Airbnb π¦β¨
- Giving Llama4 a "thinking" scratchpad is a superpower
- @GroqInc is so fast that it makes the additional "think" step tolerable.
I love everything about this! Full code below π https://t.co/E1wbHzOhRq
Ashpreet Bedix.com