ECNU/Aurora
Updated
AI & ML interests
None defined yet.
Recent Activity
View all activity
Ccloud0525
published
a
model
1 day ago
Sri-Vigneshwar-DJ
posted
an
update
2 days ago
Post
159
🏙️ 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
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
11 days ago
Post
293
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
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
17 days ago
Post
2174
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! 🚀
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
20 days ago
Post
1376
🦅 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
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
Post
1903
Genuine recommendation: You should really use this AutoHotKey macro. Save the file as
In my experience the past few months,
macros.ahk and run it. Before sending a prompt to your coding agent, press Ctrl + Alt + 1 and paste your prompt to any regular chatbot. Then send the output to the agent. This is the actual, boring, real way to "10x your prompting". Use the other number keys to avoid repeating yourself over and over again. I use this macro prolly 100-200 times per day. AutoHotKey isn't as new or hype as a lot of other workflows, but there's a reason it's still widely used after 17 years. Don't overcomplicate it.; Requires AutoHotkey v1.1+
; All macros are `Ctrl + Alt + <variable>`
^!1::
Send, Please help me more clearly articulate what I mean with this message (write the message in a code block):
return
^!2::
Send, Please make the following changes:
return
^!3::
Send, It seems you got cut off by the maximum response limit. Please continue by picking up where you left off.
returnIn my experience the past few months,
Ctrl + Alt + 1 works best with Instruct models (non-thinking). Reasoning causes some models to ramble and miss the point. I've just been using GPT-5.x for this.
Elvis-t9
authored
a
paper
21 days ago
Sri-Vigneshwar-DJ
posted
an
update
24 days 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/hawky-ai-h1-mini-1b-experimental
Sri-Vigneshwar-DJ
posted
an
update
26 days ago
Post
2955
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
https://huggingface.co/blog/Sri-Vigneshwar-DJ/the-context-layer-performance-marketing-needs
Post
2290
🚨 New tool for the
Nymbo/Tools MCP server: The new
How it works: The tool exposes the standard discover/info/resources/validate actions. Skills live in
I've included a
Caveat: On HF Spaces,
Try it out ~ https://www.nymbo.net/nymbot
Agent_Skills tool provides full support for Agent Skills (Claude Skills but open-source).How it works: The tool exposes the standard discover/info/resources/validate actions. Skills live in
/Skills under the same File_System root, and any bundled scripts run through Shell_Command, no new infrastructure required.Agent_Skills(action="discover") # List all available skills
Agent_Skills(action="info", skill_name="music-downloader") # Full SKILL.md
Agent_Skills(action="resources", skill_name="music-downloader") # Scripts, refs, assetsI've included a
music-downloader skill as a working demo, it wraps yt-dlp for YouTube/SoundCloud audio extraction.Caveat: On HF Spaces,
Shell_Command works for most tasks, but some operations (like YouTube downloads) are restricted due to the container environment. For full functionality, run the server locally on your machine.Try it out ~ https://www.nymbo.net/nymbot
Post
5233
🚀 I've just shipped a major update to the
Nymbo/Tools MCP server: the
Anthropic found 98.7% context savings using code execution with MCP, Cloudflare published similar findings. This is my open-source implementation of the same idea.
# The Problem
Traditional MCP exposes every tool definition directly to the model. With 12 tools, that's thousands of tokens consumed *before the conversation even starts*. Each tool call also passes intermediate results through the context window — a 10,000-row spreadsheet? That's all going into context just to sum a column.
# The Solution: One Tool to Rule Them All
Instead of the model making individual tool calls, it writes Python code that orchestrates the tools directly:
Don't know what tools are available? The agent can discover them at runtime:
The individual direct tool calls are all still there, but they can be disabled if using the
Agent_Terminal, a single "master tool" that cuts token usage by over 90%!Anthropic found 98.7% context savings using code execution with MCP, Cloudflare published similar findings. This is my open-source implementation of the same idea.
# The Problem
Traditional MCP exposes every tool definition directly to the model. With 12 tools, that's thousands of tokens consumed *before the conversation even starts*. Each tool call also passes intermediate results through the context window — a 10,000-row spreadsheet? That's all going into context just to sum a column.
# The Solution: One Tool to Rule Them All
Agent_Terminal wraps all 12 tools (Web_Search, Web_Fetch, File_System, Generate_Image, Generate_Speech, Generate_Video, Deep_Research, Memory_Manager, Obsidian_Vault, Shell_Command, Code_Interpreter) into a single Python code execution gateway.Instead of the model making individual tool calls, it writes Python code that orchestrates the tools directly:
# Search for Bitcoin price
result = Web_Search("current price of bitcoin", max_results=3)
print(result)Don't know what tools are available? The agent can discover them at runtime:
print(search_tools('image')) # Find tools by keyword
print(usage('Generate_Image')) # Get full docs for a specific toolThe individual direct tool calls are all still there, but they can be disabled if using the
Agent_Terminal. Try it now - https://www.nymbo.net/nymbot
- 1 reply
ContemplatorFRC
updated
a
Space
2 months ago
Post
1146
I've added an 11th tool to the
Nymbo/Tools MCP server, it's for your
# Obsidian_Vault Tool
It's basically a read-only version of the
Run the server locally and set the
# Web_Search Improvements
The
There's also a new date filter to limit results to those created in the past day, week, month, or year. Oh, and uhh, SafeSearch is now
# Web_Fetch Improvements
As context-efficient as the Markdown mode is for web browsing, sometimes it does lose important context in the conversion from HTML to Markdown. So I've added a new HTML mode to the
# A Note on Claude Skills
I've been having fun with the new
Happy building ~
Obsidian_Vault. I'd argue it's far more context-efficient than any other Obsidian MCP I've seen, and doesn't require any plugins. Also some big improvements to the Web_Search and Web_Fetch tools.# Obsidian_Vault Tool
It's basically a read-only version of the
File_System tool, but it works so well for navigating Obsidian without unnecessary context. It supports recursive (full-text) search across the entire vault, and supports offset so the agent can "scroll" through a document without re-consuming tokens.Run the server locally and set the
OBSIDIAN_VAULT_ROOT environment variable to your vault's root path. If you don't use Obsidian, this is perfectly usable as simply a read-only filesystem.# Web_Search Improvements
The
Web_Search tool previously just used DuckDuckGo as a backend search engine, but now it also supports Bing, Brave, Yahoo, and Wikipedia. Default engine is auto which provides results from all backends in recommended order. Still doesn't require any kind of API or auth for Web_Search.There's also a new date filter to limit results to those created in the past day, week, month, or year. Oh, and uhh, SafeSearch is now
off by default :)# Web_Fetch Improvements
As context-efficient as the Markdown mode is for web browsing, sometimes it does lose important context in the conversion from HTML to Markdown. So I've added a new HTML mode to the
Web_Fetch tool that basically executes a cURL request on the URL, returning the full HTML page if necessary.# A Note on Claude Skills
I've been having fun with the new
File_System and Shell_Command tools. Using Claude Skills doesn't currently work in the public HF space because of environment restrictions, but using Skills works perfectly well running locally.Happy building ~
Elvis-t9
authored
4
papers
3 months ago
D2LLM: Decomposed and Distilled Large Language Models for Semantic Search
Paper
•
2406.17262
•
Published
•
5
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
Paper
•
2409.06679
•
Published
•
4
CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects
Paper
•
2509.14856
•
Published
•
2
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Paper
•
2510.02294
•
Published
•
46
Post
2025
Two new tools added to the
Nymbo/Tools MCP server,
GPT-5-Codex proves that for many cases, shell commands really are all you need, and Claude Skills seem to lean into this. The thing is, nothing about the design of Claude Skills actually restricts them to proprietary models!
# File_System
There's a new directory inside the repo called
Files created in the public HF space live in the space's running container, and gets cleared when the space is restarted. When running the server locally, files are actually stored on disk.
# Shell_Exec
What good is a filesystem if you can't execute commands in that filesystem? This tool automatically detects if the server is running on Windows or Linux, and suggests using the appropriate shell (PowerShell/Bash). Both of these new tools require that the agent uses relative paths, rather than absolute paths. I could be convinced to back pedal on this.
# Closing Thoughts
The
File_System and Shell_Exec. You can theoretically do basically anything with these two tools, and it should enable support for many Claude Skills. GPT-5-Codex proves that for many cases, shell commands really are all you need, and Claude Skills seem to lean into this. The thing is, nothing about the design of Claude Skills actually restricts them to proprietary models!
# File_System
There's a new directory inside the repo called
Filesystem, that's the agent's "root". It can perform the following actions : list, read, write, append, mkdir, move, copy, delete, info, help. It's able to keep this all within the scope of one tool call by making the Action field required and all other fields optional. Using a filesystem shouldn't require 15 different tools.Files created in the public HF space live in the space's running container, and gets cleared when the space is restarted. When running the server locally, files are actually stored on disk.
# Shell_Exec
What good is a filesystem if you can't execute commands in that filesystem? This tool automatically detects if the server is running on Windows or Linux, and suggests using the appropriate shell (PowerShell/Bash). Both of these new tools require that the agent uses relative paths, rather than absolute paths. I could be convinced to back pedal on this.
# Closing Thoughts
The
File_System and Shell_Exec tools aren't super polished yet, I'll continue to improve the agent's instructions and UX of using the new tools. Most of my testing was done with gpt-oss-20b and if it messes up, it gets the gist after one failed tool call. It should work perfectly fine for the GPU poor.
- 1 reply
Post
1884
I've made some improvements to my custom Deep_Research tool in the
Nymbo/Tools MCP server. I've added a second LLM process and it still takes less than 1 minute to complete!
The original version of my Deep_Research tool would basically dump up to 50 fetched webpages onto the Researcher model (
# New "Filterer" Process
The new process includes another LLM call before the researcher process. The Filterer (also
# Researcher Context
The Researcher now gets only the relevant webpages, then begins writing the report. When testing with 50 initial results, the researcher would often end up with 10-20 results of relevant context.
It still takes less than a minute to accomplish everything, thanks entirely to Cerebras inference. It now takes about 35-45 seconds to complete once the tool is run.
It's also worth noting that both the Filterer and Researcher now are provided the current time/date before they see the content, reducing hallucinations caused by knowledge cutoffs.
The original version of my Deep_Research tool would basically dump up to 50 fetched webpages onto the Researcher model (
Qwen3-235B), with only a little bit of context shown from each page.# New "Filterer" Process
The new process includes another LLM call before the researcher process. The Filterer (also
Qwen3-235B) gets the query summary and the original 50 pages with low context, and decides which pages are most relevant to the research topic. The Filterer then outputs the URLs to the relevant pages, which are then re-fetched (with more context) and sent to the Researcher.# Researcher Context
The Researcher now gets only the relevant webpages, then begins writing the report. When testing with 50 initial results, the researcher would often end up with 10-20 results of relevant context.
It still takes less than a minute to accomplish everything, thanks entirely to Cerebras inference. It now takes about 35-45 seconds to complete once the tool is run.
It's also worth noting that both the Filterer and Researcher now are provided the current time/date before they see the content, reducing hallucinations caused by knowledge cutoffs.