blog-explorers (Blog-explorers)

posted an update about 7 hours ago

Post

33

🦅 Introducing Hawky AI H1 Mini 4B: A Domain-Specific Model for Performance Marketing

Hey HuggingFace community! 👋

We're excited to share our first open-source release: **Hawky AI H1 Mini 4B Experimental** - a Gemma 3 4B model fine-tuned specifically for Meta advertising and performance marketing strategy.

🎯 Why We Built This

At [Hawky.ai](https://hawky.ai), we build AI-powered creative intelligence tools for performance marketers. We work with major agencies (WPP, Madison, GroupM) and brands (TVS Motors, Tanishq, Bajaj Finserv) on campaign optimization.

We wanted to explore: Can a small, domain-specific model provide expert-level guidance on performance marketing?

Specifically, we focused on Meta's Andromeda algorithm - the AI system that now powers ad delivery across Facebook and Instagram. Understanding Andromeda is crucial for modern media buying, but the knowledge is scattered and constantly evolving.

🧠 What Makes This Different

Chain-of-Thought Reasoning
The model doesn't just answer - it **thinks through problems** step-by-step:

Sri-Vigneshwar-DJ/hawky-ai-h1-mini-4b-experimental

Reality123b

posted an update about 20 hours ago

Post

329

Happy birthday to me!!!

merve

in blog-explorers/README 1 day ago

Update README.md

#12 opened 1 day ago by

merve

Sri-Vigneshwar-DJ

posted an update 5 days ago

Post

904

Domain-specific reasoning is crucial when working with big-budget campaigns on Meta. That's why we've launched an experimental Chain-of-Thought (CoT) reasoning model for critical thinking, tailored to Meta's Andromeda algorithm-based campaign structuring and optimization.

Sri-Vigneshwar-DJ/hawky-ai-h1-mini-1b-experimental

Sri-Vigneshwar-DJ

posted an update 6 days ago

Post

2929

The recent update to Meta's ad algorithm is very difficult to crack, and even the latest models struggle to keep up with it. To address this, we've created a small experimental dataset for fine-tuning models to better tackle Meta's Andromeda algorithm: Sri-Vigneshwar-DJ/hawky-ai-andromeda-dataset

Reality123b

posted an update 8 days ago

Post

148

Thread to talk about the RAM shortage.

Guys I have RAM.

Please don't ban be for this, I know this is not directly related to AI

oopere

authored a paper 8 days ago

Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2

Paper • 2512.22671 • Published 12 days ago • 1

Sri-Vigneshwar-DJ

posted an update 10 days ago

Post

2060

I recently encountered a context graph issue in specific verticals and wrote about the importance of the context layer in performance marketing.

https://huggingface.co/blog/Sri-Vigneshwar-DJ/the-context-layer-performance-marketing-needs

prithivMLmods

in blog-explorers/README 22 days ago

[Support] Community Articles

🚀 🤝 1

88

#5 opened almost 2 years ago by

victor

ozayezerceli

authored 2 papers about 1 month ago

TurkEmbed: Turkish Embedding Model on NLI & STS Tasks

Paper • 2511.08376 • Published Nov 11, 2025 • 2

TurkEmbed4Retrieval: Turkish Embedding Model for Retrieval Task

Paper • 2511.07595 • Published Nov 10, 2025 • 1

elismasilva

posted an update about 1 month ago

Post

353

Hey everyone,

I've built and deployed Panorama FLUX, a Gradio app for creating ultra-wide panoramic images from three different text prompts using the FLUX.1-schnell model.

It uses a custom "Mixture of Diffusers" pipeline to generate and seamlessly blend each section of the image.

Key Features:
- Multi-Prompt Input: Control the left, center, and right of the scene with unique prompts.
- Seamless Blending: Choose between Cosine and Gaussian blending methods to eliminate seams between tiles.
- Optimized for FLUX.1-schnell: Designed for fast, 4-step generation with embedded guidance.
- Multi-Language Support: On-the-fly translation for prompts written in Korean and Chinese.
- Memory Efficient: Supports both custom (mmgp) and standard diffusers offloading for use on consumer GPUs or in Spaces.

This was a fun project that involved deep-diving into the FLUX architecture to get the tiling, guidance, and positional embeddings right.

Try it out!
🚀 Live Demo on Hugging Face Spaces:
elismasilva/flux-1-panorama

Jofthomas

posted an update about 1 month ago

Post

3565

The new Mistral 3 models are here !

Today, we announce Mistral 3, the next generation of Mistral models. Mistral 3 includes three state-of-the-art small, dense models (14B, 8B, and 3B) and Mistral Large 3 – our most capable model to date – a sparse mixture-of-experts trained with 41B active and 675B total parameters.

All models are released under the Apache 2.0 license.

Ministrals :
https://huggingface.co/collections/mistralai/ministral-3

Mistral Large 3:
https://huggingface.co/collections/mistralai/mistral-large-3

2 replies

·

ccocks-deca

in blog-explorers/README about 1 month ago

Card forensics using VLM localized prompt approach

2

#11 opened about 1 month ago by

vijayksagi

ozayezerceli

authored 2 papers about 2 months ago

Parrot: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs

Paper • 2511.17220 • Published Nov 21, 2025 • 17

TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval

Paper • 2511.16528 • Published Nov 20, 2025 • 22

elismasilva

posted an update about 2 months ago

Post

2568

I'm thrilled to launch SUP Toolbox! An AI tool for image restoration & upscaling using SUPIR, FaithDiff & ControlUnion. Built with Diffusers and Gradio UI featuring 14 custom components I developed.

Space Demo: elismasilva/sup-toolbox-app
App repository: https://github.com/DEVAIEXP/sup-toolbox-app
CLI repository: https://github.com/DEVAIEXP/sup-toolbox

Feedback is welcome!

2 replies

·

suayptalha

authored a paper 2 months ago

Superpositional Gradient Descent: Harnessing Quantum Principles for Model Training

Paper • 2511.01918 • Published Nov 1, 2025 • 11

Ihor

posted an update 2 months ago

Post

1259

Hey builders 👷‍♀️

We’re Knowledgator, the team behind open-source NLP models like GLiNER, GLiClass, and many other used for zero-shot text classification and information extraction.

If you’ve explored them on Hugging Face or used our frameworks from GitHub, we’d love your input:
🧩 Which of our models, like GLiNER or zero-shot classifiers, do you find helpful in your practical workflows?
🧩 How’s the setup, performance, and accuracy been for you?
🧩 Anything confusing, buggy, or missing that would make your workflow smoother?

Your feedback helps us improve speed, clarity, and stability for everyone in the open-source community.

💬 Comment directly here or join the discussion. We read every one 😉:
GitHub: https://github.com/Knowledgator
Discord: https://discord.gg/GXRcAVJQ
HuggingFace:

knowledgator

📝 Want to shape our next release?
Click here to complete this 2-min survey: https://docs.google.com/forms/d/e/1FAIpQLSdyz2UMHrMDX8S9stpBk0wyfngtKSYzwk-02mN1VNYDdTw8OQ/viewform

ccocks-deca

in blog-explorers/README 2 months ago

Pending Blog-Explorers Access Request

2

#10 opened 2 months ago by

KarthikAvinash

Blog-explorers

AI & ML interests