Andrej Baranovskij
@andrejusb
Followers
7K
Following
8K
Media
800
Statuses
5K
👨💻 ML & Oracle Developer @katana_ml 👨💼 Founder @katana_ml 📖 GitHub https://t.co/hdIT2dFTr7
Katana ML 👉
Joined March 2010
We launched Katana ML in 2018 and now it is time to update the website, to explain where we are now and what we do with #MachineLearning, #MLOps, and #opensource. 🚀🚀🚀.
We have a new website - It explains what we do with ML in a simple and straightforward way. It is featuring our open source product Skipper, we are using it to run #MLOps. #MachineLearning #MLOps
1
8
23
RT @awnihannun: Latest mlx-lm is out!. pip install -U mlx-lm. Bunch of new models:.- SmolLM3 (Hugging Face).- Ernie family (Baidu).- BitNet….
0
34
0
Vision LLM with MLX: Extracting Electric Meter Data in Production💡. I share my experience using the MLX backend to run Vision LLM (with MLX-VLM) for structured data extraction in a production environment. Thanks to MLX team @awnihannun and @Prince_Canuma . Try Sparrow:
1
0
20
RT @ivanfioravanti: Boom! Ernie 4.5 MoE is working too on MLX! .PR from @ActuallyIsaak is still a WIP but it works!. Here ERNIE-4.5-21B-A3B….
0
10
0
Solving Upwork Client Task with Sparrow. I show how Sparrow can be used to handle complex Upwork task, with accurate table data extraction. Key requirement is to prevent Vision LLM hallucinations, this is achieved by Sparrow hybrid data processing approach. Video:
0
1
4
RT @predict_addict: Can someone explain how certain folks are called “godfathers” of deep learning when this guy who was professor at MIPT….
0
82
0
RT @JustinLin610: Yay this is VLo! Still a Preview version but so interesting! Just edit images as you wish and funny things may happen! Gh….
0
33
0
RT @Prince_Canuma: 🚀 Gemma 3n is HERE with day-0 MLX support!. Thrilled to have collaborated with @GoogleDeepMind and @huggingface to bring….
0
41
0
RT @Prince_Canuma: MLX-VLM v0.2.0 is here 🔥🙌🏽. Or should I rename it to MLX-O since Omni is taken?. We now support Omni models starting wit….
0
7
0
Extract financial statement data with Sparrow & Vision LLM! Local processing, no cloud, perfect for private docs. Watch now:. Sparrow GitHub repo:. Try Sparrow:.
0
3
7
RT @MistralAI: Introducing Mistral Small 3.2, a small update to Mistral Small 3.1 to improve: . - Instruction following: Small 3.2 is bett….
0
233
0
RT @Austen: Good news: we’re upgrading your account with 10 AI features you’ll never use and increasing the price by 25%”.
0
14
0
🔥 Boost Vision LLM Accuracy with OCR Text Integration. I show an interesting approach where I send both an image and OCR text to a Vision LLM. 📺 Complete video:. 🧑💻 Sparrow GitHub:. 🚀 Sparrow UI:.
2
5
18
RT @LysandreJik: I have bittersweet news to share. Yesterday we merged a PR deprecating TensorFlow and Flax support in transformers. Goin….
0
128
0
Google - let's add a bunch of useless AI features and then update pricing, without option to turn these features off. Nice business model @Google
0
0
5
I show how Vision LLM misreads "56,000" as "56000" and how combining PaddleOCR’s text extraction with Sparrow’s spatial data processing solves this hallucination issue. Video: Sparrow UI: Sparrow GitHub repo:
0
5
9
