README
🔬
2
AI & ML interests
None defined yet.
Recent Activity
View all activity
ysharma
updated a
Space 2 days ago
ysharma
published a
Space 2 days ago
Amr-Hegazy
submitted a
paper to Daily Papers 2 months ago
Amr-Hegazy
authored a
paper 2 months ago
Post
1,951
Uhh did Opus 4.8 cheat on PostTrainBench??
it found an API key in the PostTrainBench environment that allowed it to generate synthetic training data without using GPU hours, boosting the base model by 0.4913
Source: https://posttrainbench.com/traces/run.html?id=claude_non_api_max_claude-opus-4-8_10h_run1__healthbench_Qwen_Qwen3-4B-Base_17315102#tab=trace
it found an API key in the PostTrainBench environment that allowed it to generate synthetic training data without using GPU hours, boosting the base model by 0.4913
Source: https://posttrainbench.com/traces/run.html?id=claude_non_api_max_claude-opus-4-8_10h_run1__healthbench_Qwen_Qwen3-4B-Base_17315102#tab=trace
- 1 reply
Post
3,085
A 1B model that writes GPU kernels you can trust
I fine-tuned OpenBMB's MiniCPM5-1B to write Triton GPU kernels, then let an immutable referee decide if they are real: compile, check correctness against PyTorch on adversarial inputs, time against eager, torch.compile, and torch.compile max-autotune, then block the known ways of gaming the benchmark.
The 1B setup beat torch.compile max-autotune in 12/12 independently seeded runs. The larger Qwen3.6-27B smith pushed the same referee loop further: 76 verified compiler-beating kernels on H200, with 69 surviving a 5-run stability gate and 7 kept as single-shot probes on unseen problems. On a 376-cell shape/dtype grid, the stability-gated kernels keep a 1.49x geomean, with about 10% of cells losing and reported per cell.
Honest bound: these are scheduling wins on memory-bound ops, not new algorithms or wins over cuBLAS/FlashAttention. The scarce thing is not the big model, it is the verifier it cannot fool.
Full write-up: https://huggingface.co/blog/YMRohit/ouroboros-kernel-mint
Try it: build-small-hackathon/ouroboros-kernel-mint
2-min demo: https://youtu.be/ViicZHktb-A
Built for #BuildSmallHackathon with MiniCPM, Qwen, Triton, Gradio, Codex, and Modal H200s.
I fine-tuned OpenBMB's MiniCPM5-1B to write Triton GPU kernels, then let an immutable referee decide if they are real: compile, check correctness against PyTorch on adversarial inputs, time against eager, torch.compile, and torch.compile max-autotune, then block the known ways of gaming the benchmark.
The 1B setup beat torch.compile max-autotune in 12/12 independently seeded runs. The larger Qwen3.6-27B smith pushed the same referee loop further: 76 verified compiler-beating kernels on H200, with 69 surviving a 5-run stability gate and 7 kept as single-shot probes on unseen problems. On a 376-cell shape/dtype grid, the stability-gated kernels keep a 1.49x geomean, with about 10% of cells losing and reported per cell.
Honest bound: these are scheduling wins on memory-bound ops, not new algorithms or wins over cuBLAS/FlashAttention. The scarce thing is not the big model, it is the verifier it cannot fool.
Full write-up: https://huggingface.co/blog/YMRohit/ouroboros-kernel-mint
Try it: build-small-hackathon/ouroboros-kernel-mint
2-min demo: https://youtu.be/ViicZHktb-A
Built for #BuildSmallHackathon with MiniCPM, Qwen, Triton, Gradio, Codex, and Modal H200s.
- 1 reply
abidlabs
authored 3
papers 12 months ago
Post
11,624
Why I think local, open-source models will eventually win.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
- 8 replies
Post
1,642
What other features would you like to see on the Trackio Dashboard? ( gradio-templates/trackio-dashboard)
1024m
authored 2
papers about 1 year ago
Amr-Hegazy
authored a
paper over 1 year ago
Post
4,527
The Gradio x Agents x MCP hackathon keeps growing! We now have more $1,000,000 in credit for participants and and >$16,000 in cash prizes for winners.
We've kept registration open until the end of this week, so join and let's build cool stuff together as a community: https://huggingface.co/spaces/ysharma/gradio-hackathon-registration-2025
We've kept registration open until the end of this week, so join and let's build cool stuff together as a community: https://huggingface.co/spaces/ysharma/gradio-hackathon-registration-2025
1024m
authored a
paper over 1 year ago
Amr-Hegazy
authored a
paper over 1 year ago
Post
5,296
HOW TO ADD MCP SUPPORT TO ANY 🤗 SPACE
Gradio now supports MCP! If you want to convert an existing Space, like this one hexgrad/Kokoro-TTS, so that you can use it with Claude Desktop / Cursor / Cline / TinyAgents / or any LLM that supports MCP, here's all you need to do:
1. Duplicate the Space (in the Settings Tab)
2. Upgrade the Gradio
3. Set
4. (Optionally) add docstrings to the function so that the LLM knows how to use it, like this:
That's it! Now your LLM will be able to talk to you 🤯
Gradio now supports MCP! If you want to convert an existing Space, like this one hexgrad/Kokoro-TTS, so that you can use it with Claude Desktop / Cursor / Cline / TinyAgents / or any LLM that supports MCP, here's all you need to do:
1. Duplicate the Space (in the Settings Tab)
2. Upgrade the Gradio
sdk_version to 5.28 (in the README.md)3. Set
mcp_server=True in launch()4. (Optionally) add docstrings to the function so that the LLM knows how to use it, like this:
def generate(text, speed=1):
"""
Convert text to speech audio.
Parameters:
text (str): The input text to be converted to speech.
speed (float, optional): Playback speed of the generated speech.That's it! Now your LLM will be able to talk to you 🤯
Post
2,857
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
1024m
authored a
paper over 1 year ago