Track can be with or without Gradio
and Track 2 you have to use Gradio
yes Track 1 is MCP and Track 2 is agents
Reuben fernandes PRO
Reubencf
AI & ML interests
LLM
Recent Activity
liked
a Space
36 minutes ago
MCP-1st-Birthday/anim-lab-ai
upvoted
an
article
2 days ago
AI Energy Score v2: Refreshed Leaderboard, now with Reasoning ๐ง
upvoted
an
article
4 days ago
We Got Claude to Fine-Tune an Open Source LLM
Organizations
replied to
their
post
13 days ago
ใในใใใใพใ
replied to
their
post
13 days ago
@yuki-sui
track 1 can be anything.
Track 2 you have to strictly use Gradio
replied to
their
post
13 days ago
No it is made using Next.js
replied to
their
post
13 days ago
Thanks a lot @ash-98
replied to
their
post
14 days ago
@John6666 @3ddelano @Sammy1611 @anupbhat What are your thoughts on this ?
reacted to
their
post with ๐ฅ
14 days ago
Post
2400
Hey everyone! ๐
I am thrilled to present MCP-1st-Birthday/Reuben_OS my submission for the Hugging Face MCP 1st Birthday Hackathon (Creative Track).
ReubenOS is a virtual cloud-based operating system designed specifically to act as a backend for Claude Desktop via the Model Context Protocol (MCP). It gives Claude a persistent environment to work in!
โจ Key Features
* ๐ฑ Flutter IDE: Claude can write Flutter code and I can view/execute the files directly in the ReubenOS dashboard.
* ๐ต AI Audio Studio: Integrated with ElevenLabs to generate songs and voiceovers from text prompts within Claude.
* ๐ Secure File System: A passkey-protected file system (private & public folders) to store code, JSON, and documents.
* ๐ง Gemini Integration: Access Google's Gemini model directly inside the OS.
* ๐ Quiz Engine: Ask Claude to "Create a Python quiz," and it deploys a graded interactive quiz to the web instantly.
I am thrilled to present MCP-1st-Birthday/Reuben_OS my submission for the Hugging Face MCP 1st Birthday Hackathon (Creative Track).
ReubenOS is a virtual cloud-based operating system designed specifically to act as a backend for Claude Desktop via the Model Context Protocol (MCP). It gives Claude a persistent environment to work in!
โจ Key Features
* ๐ฑ Flutter IDE: Claude can write Flutter code and I can view/execute the files directly in the ReubenOS dashboard.
* ๐ต AI Audio Studio: Integrated with ElevenLabs to generate songs and voiceovers from text prompts within Claude.
* ๐ Secure File System: A passkey-protected file system (private & public folders) to store code, JSON, and documents.
* ๐ง Gemini Integration: Access Google's Gemini model directly inside the OS.
* ๐ Quiz Engine: Ask Claude to "Create a Python quiz," and it deploys a graded interactive quiz to the web instantly.
-
- 9 replies
posted
an
update
14 days ago
Post
2400
Hey everyone! ๐
I am thrilled to present MCP-1st-Birthday/Reuben_OS my submission for the Hugging Face MCP 1st Birthday Hackathon (Creative Track).
ReubenOS is a virtual cloud-based operating system designed specifically to act as a backend for Claude Desktop via the Model Context Protocol (MCP). It gives Claude a persistent environment to work in!
โจ Key Features
* ๐ฑ Flutter IDE: Claude can write Flutter code and I can view/execute the files directly in the ReubenOS dashboard.
* ๐ต AI Audio Studio: Integrated with ElevenLabs to generate songs and voiceovers from text prompts within Claude.
* ๐ Secure File System: A passkey-protected file system (private & public folders) to store code, JSON, and documents.
* ๐ง Gemini Integration: Access Google's Gemini model directly inside the OS.
* ๐ Quiz Engine: Ask Claude to "Create a Python quiz," and it deploys a graded interactive quiz to the web instantly.
I am thrilled to present MCP-1st-Birthday/Reuben_OS my submission for the Hugging Face MCP 1st Birthday Hackathon (Creative Track).
ReubenOS is a virtual cloud-based operating system designed specifically to act as a backend for Claude Desktop via the Model Context Protocol (MCP). It gives Claude a persistent environment to work in!
โจ Key Features
* ๐ฑ Flutter IDE: Claude can write Flutter code and I can view/execute the files directly in the ReubenOS dashboard.
* ๐ต AI Audio Studio: Integrated with ElevenLabs to generate songs and voiceovers from text prompts within Claude.
* ๐ Secure File System: A passkey-protected file system (private & public folders) to store code, JSON, and documents.
* ๐ง Gemini Integration: Access Google's Gemini model directly inside the OS.
* ๐ Quiz Engine: Ask Claude to "Create a Python quiz," and it deploys a graded interactive quiz to the web instantly.
-
-
-
- 9 replies
๐ฅ
reacted to
mrmanna's
post with ๐
16 days ago
Post
1363
๐๐ฟ๐ฒ ๐ฌ๐ผ๐ ๐๐๐ถ๐น๐ฑ๐ถ๐ป๐ด ๐ฎ ๐ง๐ฟ๐๐ฒ ๐๐ป๐ผ๐๐น๐ฒ๐ฑ๐ด๐ฒ ๐๐ฎ๐๐ฒ ๐ผ๐ฟ ๐๐๐๐ ๐ฎ ๐ฆ๐บ๐ฎ๐ฟ๐ ๐ฆ๐ฒ๐ฎ๐ฟ๐ฐ๐ต ๐๐ป๐ด๐ถ๐ป๐ฒ?
๐๐ฉ๐บ ๐ข ๐ด๐ช๐ฎ๐ฑ๐ญ๐ฆ ๐ฅ๐ฐ๐ฎ๐ข๐ช๐ฏ ๐ฎ๐ฐ๐ฅ๐ฆ๐ญ ๐ฅ๐ฐ๐ฆ๐ด ๐ฎ๐ฐ๐ณ๐ฆ ๐ง๐ฐ๐ณ ๐ต๐ณ๐ถ๐ต๐ฉ ๐ต๐ฉ๐ข๐ฏ ๐ข๐ฏ๐ฐ๐ต๐ฉ๐ฆ๐ณ ๐ณ๐ฐ๐ถ๐ฏ๐ฅ ๐ฐ๐ง ๐ต๐ฐ๐ฑ-๐ฌ ๐ต๐ถ๐ฏ๐ช๐ฏ๐จ
แดแดสสษช๊ฑสแดแด แดษด แดแดแด ษชแดแด ษชษด AI Advances ย | ษดแดแด 22
Most โKnowledge basesโ today are just vector indexes with a chat UI.
Without the LLM, they know nothing. With the LLM, every answer re-rents the same knowledge in tokens.
๐๐ฒ๐ ๐๐ฎ๐ธ๐ฒ๐ฎ๐๐ฎ๐๐:
- A vector store isnโt a knowledge base; itโs a smart memory. The โknowledgeโ lives in the model you keep paying to re-read your own documents.
- Without a model (entities + relationships), you lock in two long-term costs: high tokens per question and shallow answers per question.
- A lightweight knowledge model lets you store facts once, query them cheaply, and use the LLM only for judgment and languageโโโnot for rediscovering the same truths forever.
๐๐๐น๐น ๐ฎ๐ฟ๐๐ถ๐ฐ๐น๐ฒ ๐
https://ai.gopubby.com/are-you-building-a-true-knowledge-base-or-just-a-smart-search-engine-549922e29359?sk=b755b4c54ca77ab7b6b83189be81b689
๐๐ฉ๐บ ๐ข ๐ด๐ช๐ฎ๐ฑ๐ญ๐ฆ ๐ฅ๐ฐ๐ฎ๐ข๐ช๐ฏ ๐ฎ๐ฐ๐ฅ๐ฆ๐ญ ๐ฅ๐ฐ๐ฆ๐ด ๐ฎ๐ฐ๐ณ๐ฆ ๐ง๐ฐ๐ณ ๐ต๐ณ๐ถ๐ต๐ฉ ๐ต๐ฉ๐ข๐ฏ ๐ข๐ฏ๐ฐ๐ต๐ฉ๐ฆ๐ณ ๐ณ๐ฐ๐ถ๐ฏ๐ฅ ๐ฐ๐ง ๐ต๐ฐ๐ฑ-๐ฌ ๐ต๐ถ๐ฏ๐ช๐ฏ๐จ
แดแดสสษช๊ฑสแดแด แดษด แดแดแด ษชแดแด ษชษด AI Advances ย | ษดแดแด 22
Most โKnowledge basesโ today are just vector indexes with a chat UI.
Without the LLM, they know nothing. With the LLM, every answer re-rents the same knowledge in tokens.
๐๐ฒ๐ ๐๐ฎ๐ธ๐ฒ๐ฎ๐๐ฎ๐๐:
- A vector store isnโt a knowledge base; itโs a smart memory. The โknowledgeโ lives in the model you keep paying to re-read your own documents.
- Without a model (entities + relationships), you lock in two long-term costs: high tokens per question and shallow answers per question.
- A lightweight knowledge model lets you store facts once, query them cheaply, and use the LLM only for judgment and languageโโโnot for rediscovering the same truths forever.
๐๐๐น๐น ๐ฎ๐ฟ๐๐ถ๐ฐ๐น๐ฒ ๐
https://ai.gopubby.com/are-you-building-a-true-knowledge-base-or-just-a-smart-search-engine-549922e29359?sk=b755b4c54ca77ab7b6b83189be81b689
reacted to
mrfakename's
post with ๐ฅ
17 days ago
Post
5980
Trained a model for emotion-controllable TTS based on MiMo audio on LAION's dataset.
Still very early and does have an issue with hallucinating but results seem pretty good so far, given that it is very early into the training run.
Will probably kick off a new run later with some settings tweaked.
Put up a demo here: https://huggingface.co/spaces/mrfakename/EmoAct-MiMo
(Turn ๐ on to hear audio samples)
Still very early and does have an issue with hallucinating but results seem pretty good so far, given that it is very early into the training run.
Will probably kick off a new run later with some settings tweaked.
Put up a demo here: https://huggingface.co/spaces/mrfakename/EmoAct-MiMo
(Turn ๐ on to hear audio samples)
- 5 replies
soon it will be on par with gemini 3
reacted to
paulml's
post with ๐ฅ
about 2 months ago
Post
3591
Qwen3-VL-4B is incredibly easy to fine-tune!
We've trained the first DSE model based on this model, and it's already performing at the same level as Jina v4!
While Jina Embeddings v4 is built on Qwen2.5-VL-3B (which has a non-commercial license), our model is based on Qwen3-VL-4B and released under Apache 2.0โmaking it fully commercially permissive.
Check out our DSE model here:
racineai/QwenAmann-4B-dse
We've trained the first DSE model based on this model, and it's already performing at the same level as Jina v4!
While Jina Embeddings v4 is built on Qwen2.5-VL-3B (which has a non-commercial license), our model is based on Qwen3-VL-4B and released under Apache 2.0โmaking it fully commercially permissive.
Check out our DSE model here:
racineai/QwenAmann-4B-dse
reacted to
m-ric's
post with ๐
about 2 months ago
Post
4880
STOP EVERYTHING NOW - we might finally have a radical architecture improvement over Transformers!!! ๐จ
A lone scientist just proposed Tiny Recursive Model (TRM), and it is literally the most impressive model that I've seen this year.
โก๏ธ Tiny Recursive Model is 7M parameters
โก๏ธ On ARC-AGI, it beats flagship models like Gemini-2.5-pro
Consider how wild this is: Gemini-2.5-pro must be over 10,000x bigger
and had 1,000 as many authors ๐ (Alexia is alone on the paper)
What's this sorcery?
In short: it's a very tiny Transformers, but it loops over itself at two different frequencies, updating two latent variables: one for the proposed answer and one for the reasoning.
@AlexiaJM started from the paper Hierarchical Reasoning Model, published a few months ago, that already showed breakthrough improvement on AGI for its small size (27M)
Hierarchical Reasoning Model had introduced one main feature:
๐ Deep supervision
In their model, one part (here one layer) would run at high frequency, and another would be lower frequency, running only every n steps.
They had used a recurrent architecture, where these layers would repeat many times ; but to make it work they had to do many approximations, including not fully backpropagating the loss through all layers.
Alexia studied what was useful and what wasn't, and cleaned the architecture as follows :
Why use a recurrent architecture, when you can just make it a loop?
โก๏ธ She made the network recursive, looping over itself
Why use 2 latent variables ?
โก๏ธ She provides a crystal clear explanation : the one that changes frequently is the reasoning, the one that changes at low frequency is the proposed answer.
โก๏ธ She runs ablation studies to validate that 2 is indeed optimal.
This new setup is a much more elegant way to process reasoning than generating huge chains of tokens as all flagship models currently do.
This might be the breakthrough we've been awaiting for so long!
A lone scientist just proposed Tiny Recursive Model (TRM), and it is literally the most impressive model that I've seen this year.
โก๏ธ Tiny Recursive Model is 7M parameters
โก๏ธ On ARC-AGI, it beats flagship models like Gemini-2.5-pro
Consider how wild this is: Gemini-2.5-pro must be over 10,000x bigger
and had 1,000 as many authors ๐ (Alexia is alone on the paper)
What's this sorcery?
In short: it's a very tiny Transformers, but it loops over itself at two different frequencies, updating two latent variables: one for the proposed answer and one for the reasoning.
@AlexiaJM started from the paper Hierarchical Reasoning Model, published a few months ago, that already showed breakthrough improvement on AGI for its small size (27M)
Hierarchical Reasoning Model had introduced one main feature:
๐ Deep supervision
In their model, one part (here one layer) would run at high frequency, and another would be lower frequency, running only every n steps.
They had used a recurrent architecture, where these layers would repeat many times ; but to make it work they had to do many approximations, including not fully backpropagating the loss through all layers.
Alexia studied what was useful and what wasn't, and cleaned the architecture as follows :
Why use a recurrent architecture, when you can just make it a loop?
โก๏ธ She made the network recursive, looping over itself
Why use 2 latent variables ?
โก๏ธ She provides a crystal clear explanation : the one that changes frequently is the reasoning, the one that changes at low frequency is the proposed answer.
โก๏ธ She runs ablation studies to validate that 2 is indeed optimal.
This new setup is a much more elegant way to process reasoning than generating huge chains of tokens as all flagship models currently do.
This might be the breakthrough we've been awaiting for so long!
- 4 replies
reacted to
their
post with ๐
3 months ago
Post
4263
Introducing the Nano Banana Node Editor! ๐
Now you can control and manipulate Nano Banana images with a powerful, intuitive node-based system. Explore the creative possibilities at: Reubencf/Nano_Banana_Editor
This version is clearer, more inviting, and emphasizes the creative potential of your tool.
Now you can control and manipulate Nano Banana images with a powerful, intuitive node-based system. Explore the creative possibilities at: Reubencf/Nano_Banana_Editor
This version is clearer, more inviting, and emphasizes the creative potential of your tool.
-
- 4 replies
replied to
their
post
3 months ago
The Editor Has Been Updated would love your feedback
@John6666
@Bansal123
@zhaoqiyong
@zkelo
@heyanabelle
Take care
reacted to
drvsbrkcn's
post with ๐ค
3 months ago
Post
2400
Hello everyone,
It is my first time using Hugging Face.
It is hella nice.
Take care.
It is my first time using Hugging Face.
It is hella nice.
Take care.
-
- 1 reply
replied to
their
post
3 months ago
yes pressing the โ brings up the help menu.