Post
2841
Eyyyy 50 followers ๐คฏ
- 1 reply
Kenneth Hamilton PRO
ZennyKenny
AI & ML interests
Building and enablement @ montebello.ai
Certified vibe coder
Recent Activity
updated
a dataset
4 days ago
ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset
reacted
to
ProCreations's
post
with ๐
6 days ago
Eyyyy 50 followers ๐คฏ
liked
a Space
12 days ago
reasoning-datasets-competition/README
Organizations
ZennyKenny's activity
reacted to
ProCreations's
post with ๐
6 days ago
reacted to
hesamation's
post with ๐
17 days ago
Post
3266
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
> 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
reacted to
jeffboudier's
post with ๐
19 days ago
Post
2560
Transcribing 1 hour of audio for less than $0.01 ๐คฏ
@mfuntowicz cooked with 8x faster Whisper speech recognition - whisper-large-v3-turbo transcribes at 100x real time on a $0.80/hr L4 GPU!
How they did it: https://huggingface.co/blog/fast-whisper-endpoints
1-click deploy with HF Inference Endpoints: https://endpoints.huggingface.co/new?repository=openai%2Fwhisper-large-v3-turbo&vendor=aws®ion=us-east&accelerator=gpu&instance_id=aws-us-east-1-nvidia-l4-x1&task=automatic-speech-recognition&no_suggested_compute=true
@mfuntowicz cooked with 8x faster Whisper speech recognition - whisper-large-v3-turbo transcribes at 100x real time on a $0.80/hr L4 GPU!
How they did it: https://huggingface.co/blog/fast-whisper-endpoints
1-click deploy with HF Inference Endpoints: https://endpoints.huggingface.co/new?repository=openai%2Fwhisper-large-v3-turbo&vendor=aws®ion=us-east&accelerator=gpu&instance_id=aws-us-east-1-nvidia-l4-x1&task=automatic-speech-recognition&no_suggested_compute=true
reacted to
AdinaY's
post with ๐ฅ
20 days ago
Post
2403
Bytedance is on fire this week ๐ฅ๐ฅ๐ฅ
They released Seed1.5-VL, A vision-language model for general-purpose multimodal reasoning.
Itโs not open-source, but the paper and demo are available here๐
โจ Seed1.5-VL Technical Report (2505.07062)
โจ ByteDance-Seed/Seed1.5-VL
They released Seed1.5-VL, A vision-language model for general-purpose multimodal reasoning.
Itโs not open-source, but the paper and demo are available here๐
โจ Seed1.5-VL Technical Report (2505.07062)
โจ ByteDance-Seed/Seed1.5-VL
replied to
as-cle-bert's
post
22 days ago
Whoa. Reliable open-sourced crawling software is a big win. I'll take it for a spin but I'm optimistic as this is the kind of thing I (and every other AI builder) has been building for years to avoid paying FireCrawl.
reacted to
onekq's
post with ๐ฅ
23 days ago
Post
3279
This time Gemini is very quick with API support on its 2.5 pro May release. The performance is impressive too, now it is among top contenders like o4, R1, and Claude.
onekq-ai/WebApp1K-models-leaderboard
onekq-ai/WebApp1K-models-leaderboard
reacted to
wolfram's
post with ๐ฅ
24 days ago
Post
7160
Finally finished my extensive **Qwen 3 evaluations** across a range of formats and quantisations, focusing on **MMLU-Pro** (Computer Science).
A few take-aways stood out - especially for those interested in local deployment and performance trade-offs:
1๏ธโฃ **Qwen3-235B-A22B** (via Fireworks API) tops the table at **83.66%** with ~55 tok/s.
2๏ธโฃ But the **30B-A3B Unsloth** quant delivered **82.20%** while running locally at ~45 tok/s and with zero API spend.
3๏ธโฃ The same Unsloth build is ~5x faster than Qwen's **Qwen3-32B**, which scores **82.20%** as well yet crawls at <10 tok/s.
4๏ธโฃ On Apple silicon, the **30B MLX** port hits **79.51%** while sustaining ~64 tok/s - arguably today's best speed/quality trade-off for Mac setups.
5๏ธโฃ The **0.6B** micro-model races above 180 tok/s but tops out at **37.56%** - that's why it's not even on the graph (50 % performance cut-off).
All local runs were done with LM Studio on an M4 MacBook Pro, using Qwen's official recommended settings.
**Conclusion:** Quantised 30B models now get you ~98 % of frontier-class accuracy - at a fraction of the latency, cost, and energy. For most local RAG or agent workloads, they're not just good enough - they're the new default.
Well done, Qwen - you really whipped the llama's ass! And to OpenAI: for your upcoming open model, please make it MoE, with toggleable reasoning, and release it in many sizes. *This* is the future!
A few take-aways stood out - especially for those interested in local deployment and performance trade-offs:
1๏ธโฃ **Qwen3-235B-A22B** (via Fireworks API) tops the table at **83.66%** with ~55 tok/s.
2๏ธโฃ But the **30B-A3B Unsloth** quant delivered **82.20%** while running locally at ~45 tok/s and with zero API spend.
3๏ธโฃ The same Unsloth build is ~5x faster than Qwen's **Qwen3-32B**, which scores **82.20%** as well yet crawls at <10 tok/s.
4๏ธโฃ On Apple silicon, the **30B MLX** port hits **79.51%** while sustaining ~64 tok/s - arguably today's best speed/quality trade-off for Mac setups.
5๏ธโฃ The **0.6B** micro-model races above 180 tok/s but tops out at **37.56%** - that's why it's not even on the graph (50 % performance cut-off).
All local runs were done with LM Studio on an M4 MacBook Pro, using Qwen's official recommended settings.
**Conclusion:** Quantised 30B models now get you ~98 % of frontier-class accuracy - at a fraction of the latency, cost, and energy. For most local RAG or agent workloads, they're not just good enough - they're the new default.
Well done, Qwen - you really whipped the llama's ass! And to OpenAI: for your upcoming open model, please make it MoE, with toggleable reasoning, and release it in many sizes. *This* is the future!
- 4 replies
posted
an
update
26 days ago
Post
882
Community! ๐ก๐ก๐ก
It's the last day to submit your datasets for the Reasoning Datasets Competition: https://www.bespokelabs.ai/blog/reasoning-datasets-competition
Here are my submissions:
- ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset
- ZennyKenny/cosa-benchmark-dataset
- ZennyKenny/tactical-military-reasoning-v.1.0
- ZennyKenny/tron-dataset-v.1.0
Have a look and drop a โค๏ธ or comment! Check out the entire collection of submissions here: https://huggingface.co/datasets?other=reasoning-datasets-competition
It's the last day to submit your datasets for the Reasoning Datasets Competition: https://www.bespokelabs.ai/blog/reasoning-datasets-competition
Here are my submissions:
- ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset
- ZennyKenny/cosa-benchmark-dataset
- ZennyKenny/tactical-military-reasoning-v.1.0
- ZennyKenny/tron-dataset-v.1.0
Have a look and drop a โค๏ธ or comment! Check out the entire collection of submissions here: https://huggingface.co/datasets?other=reasoning-datasets-competition
reacted to
their
post with ๐ง
27 days ago
Post
3136
After hearing the news that Marc Andreessen thinks that the only job that is safe from AI replacement is venture capital: https://gizmodo.com/marc-andreessen-says-one-job-is-mostly-safe-from-ai-venture-capitalist-2000596506 ๐ง ๐ง ๐ง
The Reasoned Capital synthetic dataset suddenly feels much more topical: ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset ๐ฅ๐ฅ๐ฅ
Really looking forward to potentially expanding this architecture and seeing how algorithmic clever investment truly is! ๐ฐ๐ฐ๐ฐ
The Reasoned Capital synthetic dataset suddenly feels much more topical: ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset ๐ฅ๐ฅ๐ฅ
Really looking forward to potentially expanding this architecture and seeing how algorithmic clever investment truly is! ๐ฐ๐ฐ๐ฐ
posted
an
update
28 days ago
Post
3136
After hearing the news that Marc Andreessen thinks that the only job that is safe from AI replacement is venture capital: https://gizmodo.com/marc-andreessen-says-one-job-is-mostly-safe-from-ai-venture-capitalist-2000596506 ๐ง ๐ง ๐ง
The Reasoned Capital synthetic dataset suddenly feels much more topical: ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset ๐ฅ๐ฅ๐ฅ
Really looking forward to potentially expanding this architecture and seeing how algorithmic clever investment truly is! ๐ฐ๐ฐ๐ฐ
The Reasoned Capital synthetic dataset suddenly feels much more topical: ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset ๐ฅ๐ฅ๐ฅ
Really looking forward to potentially expanding this architecture and seeing how algorithmic clever investment truly is! ๐ฐ๐ฐ๐ฐ
reacted to
onekq's
post with ๐
29 days ago
Post
1753
I didn't noticed that Gemini 2.5 (pro and flash) has been silently launched for API preview. Their performance is solid, but below QwQ 32B and the latest DeepSeek v3.
onekq-ai/WebApp1K-models-leaderboard
onekq-ai/WebApp1K-models-leaderboard
- 2 replies
replied to
their
post
29 days ago
Fair enough.
posted
an
update
29 days ago
Post
3362
When I heard the Reasoning Dataset Competition deadline was extended to 9 May, I knew I had time to get in one more entry. ๐ฅ๐ฅ๐ฅ
With the rise of Vibe Coding, and the potential risks that are introduced by humans letting LLMs build their apps for them, lots of people are (rightfully) concerned about the safety of the code that is hitting prod.
In response to that, I'm happy to present my final submission to the Reasoning Dataset Competition and attempt to start benchmarking the ability of LLMs to identify unsafe and / or exploitable code by way of the CoSa (Code Safety) benchmark: ZennyKenny/cosa-benchmark-dataset
Currently a curated set of 200 examples, calibrated on OpenAI's standard issue models (GPT-4.1, o4 mini, and GPT-3.5 Turbo) as "baseline performance" (70% decile). Check it out and drop a โค๏ธ if you think it could be useful or hit the Community section with suggestions / critiques.
With the rise of Vibe Coding, and the potential risks that are introduced by humans letting LLMs build their apps for them, lots of people are (rightfully) concerned about the safety of the code that is hitting prod.
In response to that, I'm happy to present my final submission to the Reasoning Dataset Competition and attempt to start benchmarking the ability of LLMs to identify unsafe and / or exploitable code by way of the CoSa (Code Safety) benchmark: ZennyKenny/cosa-benchmark-dataset
Currently a curated set of 200 examples, calibrated on OpenAI's standard issue models (GPT-4.1, o4 mini, and GPT-3.5 Turbo) as "baseline performance" (70% decile). Check it out and drop a โค๏ธ if you think it could be useful or hit the Community section with suggestions / critiques.
-
- 2 replies
Just beginning how to learn AI in general and looking for an assistant to help you set up a website? Check out one of the mainline providers like OpenAI, Mistral, DeepSeek, etc. You're going to be able to make plain English requests and have it generate some code for you.
In parallel, enroll in some HF courses (https://huggingface.co/learn) to start mastering the concepts needed to work with less guided models.
Probably worth mentioning that there is a lot more to setting up a website than just the code needed, and there are a ton of services out there (Wordpress, WebFlow, SquareSpace, etc.) that can help you from end (buying and registering a domain) to end (making it look like and do the things you want).
I'd politely suggest using the AI to walk you through that entire process, rather than generating the code you need. And for that you can probably configure your own purpose built Assistant using Hugging Chat: https://huggingface.co/chat/
reacted to
clem's
post with ๐ฅ
about 1 month ago
Post
1654
LeRobot-worldwide-hackathon
is already scheduled in 30 cities all over the world! Check if there's one in your city here: LeRobot-worldwide-hackathon/worldwide-map
Kind of surprised to see Microsoft moving into the reasoning space.
reacted to
abidlabs's
post with ๐
about 1 month ago
Post
2688
Hi folks! Excited to share a new feature from the Gradio team along with a tutorial.
If you don't already know, Gradio is an open-source Python library used to build interfaces for machine learning models. Beyond just creating UIs, Gradio also exposes API capabilities and now, Gradio apps can be launched Model Context Protocol (MCP) servers for LLMs.
If you already know how to use Gradio, there are only two additional things you need to do:
* Add standard docstrings to your function (these will be used to generate the descriptions for your tools for the LLM)
* Set
Here's a complete example (make sure you already have the latest version of Gradio installed):
This is a very simple example, but you can add the ability to generate Ghibli images or speak emotions to any LLM that supports MCP. Once you have an MCP running locally, you can copy-paste the same app to host it on [Hugging Face Spaces](https://huggingface.co/spaces/) as well.
All free and open-source of course! Full tutorial: https://www.gradio.app/guides/building-mcp-server-with-gradio
If you don't already know, Gradio is an open-source Python library used to build interfaces for machine learning models. Beyond just creating UIs, Gradio also exposes API capabilities and now, Gradio apps can be launched Model Context Protocol (MCP) servers for LLMs.
If you already know how to use Gradio, there are only two additional things you need to do:
* Add standard docstrings to your function (these will be used to generate the descriptions for your tools for the LLM)
* Set
mcp_server=True in launch()Here's a complete example (make sure you already have the latest version of Gradio installed):
import gradio as gr
def letter_counter(word, letter):
"""Count the occurrences of a specific letter in a word.
Args:
word: The word or phrase to analyze
letter: The letter to count occurrences of
Returns:
The number of times the letter appears in the word
"""
return word.lower().count(letter.lower())
demo = gr.Interface(
fn=letter_counter,
inputs=["text", "text"],
outputs="number",
title="Letter Counter",
description="Count how many times a letter appears in a word"
)
demo.launch(mcp_server=True)This is a very simple example, but you can add the ability to generate Ghibli images or speak emotions to any LLM that supports MCP. Once you have an MCP running locally, you can copy-paste the same app to host it on [Hugging Face Spaces](https://huggingface.co/spaces/) as well.
All free and open-source of course! Full tutorial: https://www.gradio.app/guides/building-mcp-server-with-gradio
- 2 replies
reacted to
lukmanaj's
post with ๐
about 1 month ago
Post
2228
Iโm excited to share that Iโve completed the Hugging Face Agents Course and earned my certificate.
Over the past few months, I explored how to build intelligent, autonomous agents using cutting-edge tools like smolagents, LlamaIndex, and LangGraph. The course covered everything from the fundamentals of agents to advanced topics like fine-tuning for function-calling, observability, evaluation, and even agents in games.
Some key content included:
1. Introduction to AI Agents
2. Agentic RAG use cases
3. Multi-framework implementation: smolagents, LlamaIndex, and LangGraph
4. Building, testing, and certifying a complete agent project
This was a hands-on, practical experience that deepened my understanding of how to design reliable, tool-using LLM agents. Looking forward to leveraging these skills in real-world applications in healthcare, logistics, and beyond.
Many thanks to the Hugging Face team for putting this together.
Letโs build safe and useful agents!
Over the past few months, I explored how to build intelligent, autonomous agents using cutting-edge tools like smolagents, LlamaIndex, and LangGraph. The course covered everything from the fundamentals of agents to advanced topics like fine-tuning for function-calling, observability, evaluation, and even agents in games.
Some key content included:
1. Introduction to AI Agents
2. Agentic RAG use cases
3. Multi-framework implementation: smolagents, LlamaIndex, and LangGraph
4. Building, testing, and certifying a complete agent project
This was a hands-on, practical experience that deepened my understanding of how to design reliable, tool-using LLM agents. Looking forward to leveraging these skills in real-world applications in healthcare, logistics, and beyond.
Many thanks to the Hugging Face team for putting this together.
Letโs build safe and useful agents!
- 7 replies
replied to
their
post
about 1 month ago
Great take. Thanks for sharing.