Build and share machine learning apps in 3 lines of Python. Part of the @Huggingface family 🤗.
- Tweets 7,923
- Following 12
- Followers 57,834
- Likes 7,030
Gradio retweeted
Tell your robot what you want, in plain words.
New in LeRobot: a vision-language model breaks your goal into skills your robot's brain already knows, steers it step by step, and answers questions as it works.
Demo: huggingface.co/spaces/lerobo…
12
28
200
18,806
Gradio retweeted
FLUX.3 Image Klein 6B just dropped on @huggingface 🔥
Base and distilled (16 steps), multi-reference editing, JSON bounding-box layouts
play with it 👇
hf.co/spaces/black-forest-la…
4
19
197
14,983
you can test out gemini's argon in gr.workflow, just enter your openrouter API key 🔑
p.s. you're not limited to html, duplicate the space and have a play around with the outputs!
huggingface.co/spaces/hmb/ar…
1
2
719
The model you need isn't on the Hub? Make it yourself!
ML Intern turns a prompt into a trained, evaluated model on the Hub. It plans, asks for a budget, smoke-tests, trains, evaluates and publishes.
6 models trained in a weeks time at ~$100 compute. Link in reply👇
11
4
30
5,055
Gradio retweeted
A series of examples and full prompts that allow you to use ML Intern effectively:
huggingface.co/blog/building…
The model you need isn't on the Hub? Make it yourself!
ML Intern turns a prompt into a trained, evaluated model on the Hub. It plans, asks for a budget, smoke-tests, trains, evaluates and publishes.
6 models trained in a weeks time at ~$100 compute. Link in reply👇
2
3
15
1,430
Gradio retweeted
Do you prefer a comfy ui-style "workflow view" or a regular gradio "app view"?
Starting from @Gradio 6.30, you don't have to choose!
3
6
11
1,928
Prompts behind all six models, what ML Intern did with each, and the full bill:
huggingface.co/blog/building…
2
3
601
You got to try ML Intern👇
And if you build something cool with it, tag us at @Gradio or @huggingface. Would love to see what you make!
huggingface.co/chat/?mode=ml…
425
Gradio retweeted
Kokoro TTS, but 10× smaller 🫰
Paradee distills Kokoro-82M into a 8M-param TTS
just 9 MB of weights can speak faster than real time on a single CPU thread and runs on your toaster
▶️ on Spaces hf.co/spaces/hugging-apps/pa…
17
111
1,092
89,040
Gradio retweeted
🚨 The incentives to share scientific knowledge openly are crumbling.
Historically, researchers shared scientific knowledge for two primary reasons: (1) the prestige conferred by discovery, and (2) a sense of expanding the pool of human knowledge. Even within industry, scientific discovery was far too vast an endeavor for a single scientist or team to tackle alone. So scientists explored different frontiers, usually published their findings, and collectively moved the field forward.
However, as more scientific knowledge is uncovered simply by throwing massive compute at autonomous agents with minimal human intervention, these incentives are breaking down: (1) discoveries are becoming commoditized. If anyone could have found the same result simply by running the same agentic prompt with enough compute, the prestige of discovery and the pride in one's work disappears, a shift we are already witnessing in software engineering. (2) the explosion of low-quality, low-barrier publications makes genuine breakthroughs increasingly difficult to filter, discover, and appropriately credit. (3) and for companies, keeping discoveries proprietary is increasingly advantageous. Instead of publishing and waiting for the broader scientific community to build upon the work, an organization can simply turn its own compute back onto the problem to iterate faster internally.
In the short term, the incentives reward secrecy. But my goal -- and at Hugging Face, our goal -- is the sustainable, long-term expansion of human knowledge that survives individual, closed companies. So we have to build new tools that reward and facilitate open sharing of knowledge. If agents are accelerating discovery, we are going to figure out how to use agents and other tools to preserve scientific integrity.
Starting with this: Paper Reproductions with ML Intern -- we’ve made it possible to take a published paper and task agents with independently reproducing its experiments, helping create more signals (e.g. open artifacts) that can help identify high-quality work.
8
9
46
45,785
Gradio retweeted
The Windows launch event today has mentioned "local AI" 41 times (so far) 🤯
It is very cool to see llama.cpp on the big stage in todays Windows event!
The software and hardware stacks are finally coming together. Our community has put a lot of hard work in the past years and it shows.
Looking forward to more users embracing local AI.
4
7
31
7,321
Gradio retweeted
🤗💎 Such an exciting week for open-source, congrats to the @GoogleGemma @GoogleDeepMind teams!
The @huggingface demos using @gradio are 🧑🍳🤌:
Introducing EmbeddingGemma 2, our new open embeddings model for on-device use cases!
👀 Code, image, video, audio, and text embeddings
🎛️ Modular footprint (270M text/code up to 740M full multimodal)
🧪 Matryoshka embeddings (truncate down to 128d for 6x storage savings)
🚀 +14% boost on MTEB Code vs. v1
🤗 Apache 2.0 licenseCheck out the complete developer guide with code samples:
6
7
104
16,633