Clem ๐ค PRO
AI & ML interests
Recent Activity
Organizations
clem's activity


A beautiful massive building in the center of a colorful beautiful super futuristic sunny city with flying cars. At the top of the building there's a massive neon sign in yellow that says "Hugging Face"


Two HF emojis conversing about the benefits of open source AI

Two fearful mice in the foreground whispering "OK I think the coast is clear now" while a large menacing cat sits in the background watching them

ASMR of Huggingface ML engineer inside a futuristic glass work pod typing on mechanical keyboard in a rainy mossy forest


a giant hugging face emoji balloon soars over iconic global landmarks. Diverse crowds below gaze up in awe. Feature dynamic scenes and a soundscape of gentle balloon whooshes, bustling city ambiences, crowd murmurs of wonder.

Pirate ship gliding through a neon-lit digital ocean of cyber stars and galaxies, flying a black flag marked with the hugging-face emoji. A deep voice echoes at the end: "It's more fun to be a pirate than join the Navy. Become a pirate. Join open source.


Model: BAAI/robobrain-681e1389c64d06b3e4a45e44
Dataset: BAAI/ShareRobot
โจ Task decomposition into 20+ precise actions
โจ Operable region detection (e.g: teapot handles, drawers)
โจ Motion trajectory prediction to avoid collisions


Check if there's one in your city here: LeRobot-worldwide-hackathon/worldwide-map


We need more of this from all other big tech to make the AI more open, collaborative and beneficial to all!

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 ๐คฏ

We're trying to change this by releasing ChatUI-energy, the first interface where you see in real-time what energy your AI conversations consume. Great work from @jdelavande powered by spaces & TGI, available for a dozen of open-source models like Llama, Mistral, Qwen, Gemma and more.
jdelavande/chat-ui-energy
Should all chat interfaces have this? Just like ingredients have to be shown on products you buy, we need more transparency in AI for users!

What's your favorite? http://hf.co/spaces