Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

Connecting individuals with innovation: Emancipating and Truly Federalizing Private Intelligence

Recent Activity

Goekdeniz-Guelmez  authored a paper about 1 month ago
Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models
upgraedd  new activity about 1 month ago
IntelligentEstate/README:immutable-reality
suayptalha  authored a paper 3 months ago
Superpositional Gradient Descent: Harnessing Quantum Principles for Model Training
View all activity

Sri-Vigneshwar-DJ 
posted an update about 2 hours ago
view post
Post
26
🏙️ Hugging Face Community Post
Title: 🧬 Experimenting with "Dynamic Chaos" in Tamil SLMs

Hi everyone! I just published a new experimental study on Small Language Model (SLM) resilience.

I took the Qwen2.5-0.5B model and put it through a "Chaos Phase" to see how much weight data a tiny model can lose before its understanding of classical Tamil grammar breaks.

Key highlights of the study:

Target Data: Fine-tuned on the Thirukkural (1,330 couplets + modern explanations).
The Chaos Step: Applied 20% random weight pruning but implemented "Layer Protection" for the Token Embeddings and LM Head to keep the characters readable.
Compression: 4-bit (Q4_K_M) quantization for extreme efficiency.
Result: A surrealist classical Tamil model that is ultra-light (~300MB) and ultra-fast!

Check out the model and the experiment logic here: Sri-Vigneshwar-DJ/qwen-tamil-chaos-v1
mitkox 
posted an update 5 days ago
view post
Post
1420
GLM-4.7-Flash is fast, good and cheap.
3,074 tokens/sec peak at 200k tokens context window on my desktop PC.
Works with Claude Code and opencode for hours. No errors, drop-in replacement of the Anthropic cloud AI.
MIT licensed, open weights, free for commercial use and modifications.
Supports speculative decoding using MTP, which is highly effective in mitigating latency.
Great for on device AI coding as AWQ 4bit at 18.5 GB. Hybrid inference on a single consumer GPU + CPU RAM.
·
Sri-Vigneshwar-DJ 
posted an update 8 days ago
view post
Post
283
Performance Marketing meets "Thinking Mode" 🧠

I’m excited to release hawky-ai-Qwen3-0.6B-Marketing-MoT, a specialized SLM designed for deep strategic reasoning in performance marketing.

While small at 0.6B parameters, this model punches way above its weight class by utilizing a Mixture of Thoughts (MoT) framework. It doesn't just give you an answer; it thinks through the logic of Meta Ads scaling, GA4 attribution, and unit economics before providing a strategic recommendation.

Key Features:

Thinking-First: Trained on 1,500+ critical thinking scenarios.
MoT Framework: 5 distinct reasoning styles (Linear, Exploratory, Critical, Deconstructive, Analogical).
SLM Speed: Perfect for low-latency, high-precision marketing audits.
Check it out on Hugging Face: 🔗 Sri-Vigneshwar-DJ/hawky-ai-Qwen3-0.6B-Marketing-MoT
takarajordan 
posted an update 10 days ago
Sri-Vigneshwar-DJ 
posted an update 15 days ago
view post
Post
2169
Introducing Hawky-AI H1 4B PM: The First Open-Source LLM for Performance Marketing 🎯

Hey HF Community! 👋

Just released the first LLM fine-tuned specifically for Performance Marketing.
What is it?
Gemma 3 4B distilled from Claude Opus 4.5 with expert-level marketing knowledge.
Covers:
📱 Meta Ads (campaign structure, bidding, scaling, creative fatigue)
🔍 Google Ads (Quality Score, Performance Max, lead gen)
📊 Measurement (ROAS vs MER, incrementality, LTV:CAC)
🎨 Creative Strategy (hook rates, A/B testing, funnel creative)
Why we built it:
Generic LLMs say "optimize your targeting" — not helpful. This model gives specific frameworks like "frequency at 4.5 + CTR drop = creative fatigue, here's the fix..."
Technical:

Base: Gemma 3 4B
Method: QLoRA (r=64)
Teacher: Claude Opus 4.5

🔗 Model: Sri-Vigneshwar-DJ/hawky-ai-H1-4b-PM
Built by Hawky.ai

Try it and let us know what you think! 🚀
Sri-Vigneshwar-DJ 
posted an update 18 days ago
view post
Post
1373
🦅 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
Sri-Vigneshwar-DJ 
posted an update 22 days ago
view post
Post
931
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
mitkox 
posted an update 23 days ago
view post
Post
3280
I just stress-tested the Beast: MiniMax-M2.1 on Z8 Fury G5.
2101 tokens/sec. FORTY concurrent clients. That's 609 t/s out, 1492 t/s in. The model outputs fire faster than I can type, but feeds on data like a black hole on cheat day.
But wait, there's more! Threw it into Claude Code torture testing with 60+ tools, 8 agents (7 sub-agents because apparently one wasn't enough chaos). It didn't even flinch. Extremely fast, scary good at coding. The kind of performance that makes you wonder if the model's been secretly reading Stack Overflow in its spare time lol
3 months ago, these numbers lived in my "maybe in “2030 dreams. Today it's running on my desk AND heaths my home office during the winter!
·
Sri-Vigneshwar-DJ 
posted an update 24 days ago
view post
Post
2954
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
Sri-Vigneshwar-DJ 
posted an update 28 days ago
csabakecskemeti 
posted an update about 1 month ago
view post
Post
3202
Just sharing a result of a homelab infrastructure experiment:

I've managed to setup a distributed inference infra at home using a DGX Spark (128GB unified gddr6) and a linux workstation with an RTX 6000 Pro (96GB gddr7) connected via 100Gbps RoCEv2. The model I've used (https://lnkd.in/gx6J7YuB) is about 140GB so could not fit either of the GPU. Full setup and tutorial soon on devquasar.com



Screen recording:
https://lnkd.in/gKM9H5GJ
·
Goekdeniz-Guelmez 
authored a paper about 1 month ago
upgraedd 
in IntelligentEstate/README about 1 month ago

immutable-reality
#2 opened about 1 month ago by
upgraedd
mitkox 
posted an update about 2 months ago
view post
Post
2375
Got to 1199.8 tokens/sec with Devstral Small -2 on my desktop GPU workstation. vLLM nightly.
Works out of the box with Mistral Vibe. Next is time to test the big one.
·
takarajordan 
posted an update about 2 months ago
csabakecskemeti 
posted an update about 2 months ago
csabakecskemeti 
posted an update about 2 months ago
view post
Post
2090
Looking for some help to test an INT8 Deepseek 3.2:
SGLang supports Channel wise INT8 quants on CPUs with AMX instructions (Xeon 5 and above AFAIK)
https://lmsys.org/blog/2025-07-14-intel-xeon-optimization/

Currently uploading an INT8 version of Deepseek 3.2 Speciale:
DevQuasar/deepseek-ai.DeepSeek-V3.2-Speciale-Channel-INT8

I cannot test this I'm on AMD
"AssertionError: W8A8Int8LinearMethod on CPU requires that CPU has AMX support"
(I assumed it can fall back to some non optimized kernel but seems not)

If anyone with the required resources (Intel Xeon 5/6 + ~768-1TB ram) can help to test this that would be awesome.

If you have hints how to make this work on AMD Threadripper 7000 Pro series please guide me.

Thanks all!
·
takarajordan 
posted an update 2 months ago
view post
Post
3200
Two weeks ago I had an engaging discussion with locals in Cockermouth about AI and the broader industry, a reminder that hearing candid perspectives beyond our professional circles is invaluable and something anyone working full-time in this field should make time for.

Thank you!
mitkox 
posted an update 2 months ago
view post
Post
3181
I run 20 AI coding agents locally on my desktop workstation at 400+ tokens/sec with MiniMax-M2. It’s a Sonnet drop-in replacement in my Cursor, Claude Code, Droid, Kilo and Cline peak at 11k tok/sec input and 433 tok/s output, can generate 1B+ tok/m.All with 196k context window. I'm running it for 6 days now with this config.

Today max performance was stable at 490.2 tokens/sec across 48 concurrent clients and MiniMax M2.

Z8 Fury G5, Xeon 3455, 4xA6K. Aibrix 0.5.0, vLLM 0.11.2,
·
csabakecskemeti 
posted an update 3 months ago
view post
Post
311
Recently there are so much activity on token efficient formats, I've also build a package (inspired by toon).

Deep-TOON

My goal was to token efficiently handle json structures with complex embeddings.

So this is what I've built on the weekend. Feel free try:

https://pypi.org/project/deep-toon/0.1.0/