AIZeroToHero (AI Zero to Hero)

posted an update about 10 hours ago

Post

80

Just released a new dataset designed for training reasoning models on Meta (Facebook/Instagram) advertising fatigue detection!

What is it? A GRPO (Group Relative Policy Optimization) training dataset with 200+ carefully crafted scenarios covering:

🔍 Fatigue Signal Detection: CTR drops, CPM spikes, frequency analysis
🩺 Performance Diagnosis: Root cause analysis frameworks
📋 Strategy: Creative refresh cadence, testing frameworks
📊 Analysis: ROI calculations, metric interpretation
Why GRPO? GRPO training helps models learn structured reasoning. Each response follows the <thinking> and <answer> format.

Check it out here: Sri-Vigneshwar-DJ/meta-fatigue-grpo-dataset

Sri-Vigneshwar-DJ

posted an update 10 days ago

Post

190

🏙️ 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

Sri-Vigneshwar-DJ

posted an update 18 days ago

Post

303

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

Sri-Vigneshwar-DJ

posted an update 25 days ago

Post

2179

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 27 days ago

Post

1379

🦅 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 about 1 month ago

Post

933

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 about 1 month ago

Post

2956

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 about 1 month ago

Post

2074

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

hesamation

posted an update 2 months ago

Post

3010

this is big... 50 AI researchers from Bytedance, Alibaba, Tencent, and other labs/universities just published a 300-page paper with surprising lessons about coding models and agents (data, pre and post-training, etc).

key highlights:

> small LLMs can beat proprietary giants
RL (RLVR specifically) gives small open-source models an edge over big models in reasoning. a 14B model trained with RLVR on high-quality verified problems can match the performance of OpenAI's o3.

> models have a hard time learning Python.
mixing language models during pre-training is good, but Python behaves different from statically typed languages. languages with similar syntax (Java and C#, or JavaScript and TypeScript) creates high positive synergy. mixing Python heavily into the training of statically typed languages can actually hurt because of Python's dynamic typing.

> not all languages are equal (coding scaling laws)
the amount of data required to specialize a model on a language drastically depends on the language. paper argues like C# and Java are easier to learn (less training data required). languages like Python and Javascript are actually more tricky to learn, ironically (you see AI most used for these languages :)

> MoE vs Dense (ability vs stability)
MoE models offer higher capacity, but are much more fragile during SFT than dense models. hyperparams in training have a more drastic effect in MoE models, while dense models are more stable. MoE models also require constant learning rate schedules to avoid routing instability.

> code models are "insecure" by default (duh)
training on public repos makes models learn years of accumulated insecure coding patterns. safety fine-tuning often fails to work much on code. a model might refuse to write a hate speech email but will happily generate a SQL-injection vulnerable function because it "works."

read the full paper:
From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence (2511.18538)

1 reply

·

Sri-Vigneshwar-DJ

posted an update 4 months ago

Post

354

Do you think domain-specific embedding fine-tuners are needed?
I've been working with embeddings for marketing use cases and noticed something: most embeddings don't get marketing concepts very well. They're trained in general-purpose ways.
The Issue I'm Seeing
When I search marketing content with general embeddings:

"organic growth" returns farming articles
"conversion funnel" matches industrial equipment
"brand lift" doesn't connect to campaign effectiveness
Marketing jargon like CAC, ROAS, CTR aren't properly understood

My Question
Do you think domain-specific embeddings are needed for marketing?
Some thoughts:

Marketing has its own vocabulary and concept relationships
General models trained on Wikipedia/web crawl miss these nuances
But is fine-tuning worth the effort vs just using more retrieval tricks?

Quick Example
I fine-tuned all-mpnet-base-v2 on ~1000 marketing concept pairs and saw 15-20% better retrieval accuracy. But I'm curious:

Has anyone else tried this for marketing or other domains?
When do you think domain-specific embeddings are actually necessary vs overkill?
Are there better approaches I'm missing?

https://huggingface.co/blog/Sri-Vigneshwar-DJ/why-your-marketing-rag-system-needs-domain-specifi

6 replies

·

Sri-Vigneshwar-DJ

posted an update 4 months ago

Post

4439

🚀 Exciting News! We've released a Performance Marketing Expert Dataset from Hawky.ai [www.hawky.ai]

Hawky-ai

This dataset empowers AI models with cutting-edge strategies for Meta, Google Ads, and TikTok campaigns. It includes:
1. Multi-platform strategies for e-commerce, DTC, B2B, and more
2. Creative optimization and audience targeting insights
3. ROI-driven recommendations based on 2025 best practices

Sri-Vigneshwar-DJ/Performance-Marketing-Data

Sri-Vigneshwar-DJ

posted an update 4 months ago

Post

3340

🚀 Qwen3-Omni for Marketing: A Game-Changer

Just wanted to share something exciting I've been exploring—Qwen3-Omni and how it's transforming marketing workflows.

What makes it special? At Hawky.ai we are started experimenting with Qwen3 recently for Analysis and Optimization.

Unlike traditional tools that look at text, images, or audio separately, Qwen3-Omni analyzes everything together. It handles 119 languages, processes 40-minute audio sequences, and understands both images and videos—all at once.

The cool part? It's 2-3x faster than similar models thanks to its MoE architecture.

Real applications I'm seeing:
Ad Analysis: It scores video ads by combining visual elements, audio tone, and text—giving 25% better CTR predictions than single-mode tools.
Campaign Localization: Drop in one ad, get 10 localized versions with native voiceovers in under a minute. Perfect for testing across markets.

Market Research: Feed it competitor content, podcasts, or UGC videos. It extracts actionable insights like "3-second hooks boost retention by 15%" and saves about 70% of analysis time.

Quality Checks: Automatically catches lip-sync errors and audio-visual mismatches.

Full technical breakdown: https://huggingface.co/blog/Sri-Vigneshwar-DJ/hawky-aiqwen3-omni-advanced-architecture-and-marke

Has anyone else been experimenting with multimodal models for marketing? Would love to hear what you're building!

#MultimodalAI #MarTech #OpenSource

hesamation

posted an update 5 months ago

Post

11239

a senior engineer at google just dropped a 400-page free book on docs for review: agentic design patterns.

the table of contents looks like everything you need to know about agents + code:
> advanced prompt techniques
> multi-agent patterns
> tool use and MCP
> you name it

read it here: https://docs.google.com/document/d/1rsaK53T3Lg5KoGwvf8ukOUvbELRtH-V0LnOIFDxBryE/edit?tab=t.0#heading=h.pxcur8v2qagu

you can also pre-order on Amazon (published by Springer) and the royalties goes to Save the Children: https://www.amazon.com/Agentic-Design-Patterns-Hands-Intelligent/dp/3032014018/

hesamation

posted an update 7 months ago

Post

4153

longer context doesn't generate better responses. it can even hurt your llm/agent. 1M context window doesn't automatically make models smarter as it's not about the size; it's how you use it.

here are 4 types of context failure and why each one happens:

1. context poisoning: if hallucination finds its way into your context, the agent will rely on that false information to make its future moves. for example if the agent hallucinates about the "task description", all of its planning to solve the task would also be corrupt.

2. context distraction: when the context becomes too bloated, the model focuses too much on it rather than come up with novel ideas or to follow what it has learned during training. as Gemini 2.5 Pro technical report points out, as context grows significantly from 100K tokens, "the agent showed a tendency toward favoring repeating actions from its vast history rather than synthesizing novel plans".

3. context confusion: everyone lost it when MCPs became popular, it seemed like AGI was achieved. I suspected there is something wrong and there was: it's not just about providing tools, bloating the context with tool use derails the model from selecting the right one! even if you can fit all your tool metadata in the context, as their number grows, the model gets confused over which one to pick.

4. Context Clash: if you exchange conversation with a model step by step and provide information as you go along, chances are you get worse performance rather than providing all the useful information at once. one the model's context fills with wrong information, it's more difficult to guide it to embrace the right info. agents pull information from tools, documents, user queries, etc. and there is a chance that some of these information contradict each other, and it's not good new for agentic applications.

check this article by Drew Breunig for deeper read: https://www.dbreunig.com/2025/06/26/how-to-fix-your-context.html?ref=blog.langchain.com

2 replies

·

hesamation

posted an update 7 months ago

Post

5375

in case you didn’t know, Claude now has a developer training course with certificates,

this is better than anything you can find on Coursera.

covers Claude Code, MCP and its advanced topics and even more:

https://www.anthropic.com/learn/build-with-claude

hesamation

posted an update 8 months ago

Post

2943

this repo is gold! a collection of LLM apps with multi-agents, MCP, RAG and so much more.

the best way to learn is by building, and this repo provides the blueprint.

Repo: https://github.com/Shubhamsaboo/awesome-llm-apps

hesamation

posted an update 8 months ago

Post

2803

I really like how this seven-stage pipeline was laid out in the Ultimate Guide to Fine-Tuning book.

It gives an overview, then goes into detail for each stage, even providing best practices.

It’s 115 pages on arxiv, definitely worth a read.

Check it out: https://arxiv.org/abs/2408.13296

hesamation

posted an update 9 months ago

Post

3668

60+ Generative AI projects for your resume. grind this GitHub repo if you want to level up:
> LLM fine-tuning and applications
> advanced RAG apps
> Agentic AI projects
> MCP and A2A (new)

GitHub: https://github.com/aishwaryanr/awesome-generative-ai-guide/blob/main/resources/60_ai_projects.md

hesamation

posted an update 9 months ago

Post

3132

this book actually exists for free, “the little book of deep learning”. best to refresh your mind about DL basics:
> foundations of machine learning
> how models train
> common layers (dropout, pooling…)
> basic intro to LLMs
actually optimized for mobile.

Book: https://fleuret.org/public/lbdl.pdf

hesamation

posted an update 10 months ago

Post

3013

The best researchers from DeepSeek, OpenAI, Microsoft, and ByteDance explored RL and Reasoning in LLMs,

Here's some of their key findings:

1/ RL can further improve distilled models. These models are essentially SFT fine-tuned with the data generated by larger models, and the SFT+RL combo does not disappoint.

This is verified in the DeepSeek-R1 paper.

2/ both GRPO and PPO algorithms suffer from length bias; they encourage longer responses. This can be tackled by introducing explicit rewards based on the length of the answer.

3/Most reasoning research is focused on code and math. But training models on logic puzzles improves them for mathematical tasks too.

This shows the RL reasoning is generalized beyond the specific domain knowledge.

Previous research also shows RL can be a great generalizer.

4/The reasoning might not be only induced by RL; it might already be hidden in the base models due to the pre-training and CoT data they were trained on.

So while RL does wake up the reasoning beast, maybe it's not the only solution (e.g. other methods such as distillation)

5/ back to the length bias; reasoning models tend to generate longer responses for wrong answers. RL might be the culprit.

RL favours longer answers when the reward is negative, to dilute the penalty per individual token and lower the loss.

This might explain the "aha" moments!

6/ OpenAI's competitive programming paper showed an interesting finding:

o3 can learn its own test-time strategies (like writing an inefficient but correct solution to verify the answer of an optimized solution)

RL helps LLMs develop their own reasoning & verification methods.
The recent article by @rasbt helped me a lot in getting a broad view of the recent research on reasoning models.

He also lists more influential papers on this topic, It's a must-read if you're interested.

check it out 👇
https://magazine.sebastianraschka.com/p/the-state-of-llm-reasoning-model-training

AI & ML interests

Team members 48

AIZeroToHero's activity