Feather DB ā Living Context Engine
šŖ¶
Search and explore AI product intel with semantic graph queries
AI & ML interests
None defined yet.
Sri-Vigneshwar-DJĀ
updated a
Space 3 months ago
Sri-Vigneshwar-DJĀ
updated a
dataset 3 months ago
Sri-Vigneshwar-DJĀ
updated a
Space 3 months ago
Sri-Vigneshwar-DJĀ
updated a
dataset 3 months ago
Sri-Vigneshwar-DJĀ
posted an update 3 months ago
Post
176
We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) ā 500 questions across real multi-session conversations, up to 115K tokens each.
**Score: 0.693** Ā· GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**
Per-axis breakdown:
ā Info-extraction: **0.942**
ā Knowledge-update: **0.714**
ā Multi-session: **0.606**
ā Temporal: **0.477** ā the hard one, Phase 9 addresses this
Architecture: Hybrid BM25+dense Ā· adaptive temporal decay Ā· embedded (no server) Ā· p50 = 0.19ms Ā· MIT
Raw results + audit JSONs: Hawky-ai/longmemeval-results
We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) ā 500 questions across real multi-session conversations, up to 115K tokens each.
**Score: 0.693** Ā· GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**
Per-axis breakdown:
ā Info-extraction: **0.942**
ā Knowledge-update: **0.714**
ā Multi-session: **0.606**
ā Temporal: **0.477** ā the hard one, Phase 9 addresses this
Architecture: Hybrid BM25+dense Ā· adaptive temporal decay Ā· embedded (no server) Ā· p50 = 0.19ms Ā· MIT
pip install feather-dbRaw results + audit JSONs: Hawky-ai/longmemeval-results
Feather DB v0.8.0 ā LongMemEval benchmark results + open questions on temporal reasoning
#1 opened 3 months ago
by 
Sri-Vigneshwar-DJ
Sri-Vigneshwar-DJĀ
published a
dataset 3 months ago
Sri-Vigneshwar-DJĀ
updated a
dataset 4 months ago
Sri-Vigneshwar-DJĀ
published a
dataset 4 months ago
Sri-Vigneshwar-DJĀ
updated a
Space 4 months ago
Sri-Vigneshwar-DJĀ
published a
Space 4 months ago
Sri-Vigneshwar-DJĀ
published 2
Spaces 5 months ago
Sri-Vigneshwar-DJĀ
published a
dataset 5 months ago
Sri-Vigneshwar-DJĀ
posted an update 6 months ago
Post
1472
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:
š Fatigue Signal Detection: CTR drops, CPM spikes, frequency analysis
š©ŗ Performance Diagnosis: Root cause analysis frameworks
š Strategy: Creative refresh cadence, testing frameworks
š 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
What is it? A GRPO (Group Relative Policy Optimization) training dataset with 200+ carefully crafted scenarios covering:
š Fatigue Signal Detection: CTR drops, CPM spikes, frequency analysis
š©ŗ Performance Diagnosis: Root cause analysis frameworks
š Strategy: Creative refresh cadence, testing frameworks
š 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-DJĀ
posted an update 7 months ago
Post
249
šļø Hugging Face Community Post
Title: š§¬ 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
Title: š§¬ 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-DJĀ
posted an update 7 months ago
Post
336
Performance Marketing meets "Thinking Mode" š§
Iām 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: š Sri-Vigneshwar-DJ/hawky-ai-Qwen3-0.6B-Marketing-MoT
Iām 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: š Sri-Vigneshwar-DJ/hawky-ai-Qwen3-0.6B-Marketing-MoT
Sri-Vigneshwar-DJĀ
posted an update 7 months ago
Post
2214
Introducing Hawky-AI H1 4B PM: The First Open-Source LLM for Performance Marketing šÆ
Hey HF Community! š
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:
š± Meta Ads (campaign structure, bidding, scaling, creative fatigue)
š Google Ads (Quality Score, Performance Max, lead gen)
š Measurement (ROAS vs MER, incrementality, LTV:CAC)
šØ Creative Strategy (hook rates, A/B testing, funnel creative)
Why we built it:
Generic LLMs say "optimize your targeting" ā 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
š Model: Sri-Vigneshwar-DJ/hawky-ai-H1-4b-PM
Built by Hawky.ai
Try it and let us know what you think! š
Hey HF Community! š
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:
š± Meta Ads (campaign structure, bidding, scaling, creative fatigue)
š Google Ads (Quality Score, Performance Max, lead gen)
š Measurement (ROAS vs MER, incrementality, LTV:CAC)
šØ Creative Strategy (hook rates, A/B testing, funnel creative)
Why we built it:
Generic LLMs say "optimize your targeting" ā 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
š Model: Sri-Vigneshwar-DJ/hawky-ai-H1-4b-PM
Built by Hawky.ai
Try it and let us know what you think! š
Sri-Vigneshwar-DJĀ
posted an update 7 months ago
Post
1397
š¦
Introducing Hawky AI H1 Mini 4B: A Domain-Specific Model for Performance Marketing
Hey HuggingFace community! š
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.
šÆ 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.
š§ 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
Hey HuggingFace community! š
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.
šÆ 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.
š§ 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-DJĀ
posted an update 7 months ago
Post
950
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/hawky-ai-h1-mini-1b-experimental