Using my old Midjourney V2 generations to test @everartai
's upcoming upscaler
@skirano
-
Testing EverArt Upscaler with Midjourney V2 Generations
By
–
-
Mistral and MLX for Local AI Model Deployment
By
–
Either that or just mistral. Locally using MLX, I already did a few!
-
Excitement Growing for Favorite LLM Evolution
By
–
Thanks for making this! I am excited to see it evolve even more. Definitely one of my favorite LLMs at the moment.
-
Google’s AI Model Receives Positive Reassessment From Community
By
–
I think you're all too hard on Google. This model is really solid.
-
Finetuning LLM on personal tweets for custom model
By
–
Right? Doing this to finetune an LLM on my tweets btw
-
Sora’s Video Captioning Capabilities Excite AI Community
By
–
Yeah, me too! The creation of Sora pretty much confirms they have an amazing video captioner, so I am excited for that!
-
Gemini 1.5 Pro organizes tweets into JSON format automatically
By
–
Watch Gemini 1.5 Pro collect all my tweets from a video where I scroll through my feed, and neatly organize them into a JSON format.
— Pietro Schirano (@skirano) 22 février 2024
It's even smart enough to discern between tweets, retweets, and quotes.
Best scraper tool on the planet! ⚡️ pic.twitter.com/pONWg0EhFTWatch Gemini 1.5 Pro collect all my tweets from a video where I scroll through my feed, and neatly organize them into a JSON format. It's even smart enough to discern between tweets, retweets, and quotes. Best scraper tool on the planet!
-
Video Breakdown Due to Excessive Token Count Limitation
By
–
The full video is well over 1 million tokens, which is why I broke it down. Just 30 minutes is already 500k tokens.
-
Token Optimization and Custom AI Chips for Scaling
By
–
Tokens are a function of how optimized your tokenization system is, as well as your embeddings. Therefore, new breakthroughs can emerge that don't require an enormous amount of GPU power. Sam needs money to create his own chips and scale up more quickly. We've seen that Sora's