Gemma 4 Technical Report
Paper โข 2607.02770 โข Published โข 41
AI & ML interests
Webhooks are now publicly available on Hugging Face!
Recent Activity
View all activity
osansevieroย
authored a
paper about 11 hours ago
osansevieroย
submitted a
paper to Daily Papers 2 days ago
Post
2061
Sharing how I built the LongCat-Video-Avatar 1.5 Space (+500k views on X) in one agent session. Gave a coding agent its own AI lab on ZeroGPU, framed the goal, walked away. It designed, deployed, tested against the live API, fixed, shipped.
Full recipe with the copy-paste prompt: https://huggingface.co/blog/victor/building-zerogpu-spaces-autonomously
Full recipe with the copy-paste prompt: https://huggingface.co/blog/victor/building-zerogpu-spaces-autonomously
- 1 reply
satpalsrย
submitted a
paper to Daily Papers about 2 months ago
satpalsrย
authored a
paper about 2 months ago
Post
198
We're open-sourcing our infra with 10M+ frames of dataset!
We're releasing Stera, an open-source infra that turns an off-the-shelf device in your pocket into a high-fidelity multimodal data pipeline. It's built around four layers. Capture โ Process โ Evaluate โ Export.
Stera Capture removes the need for bespoke/gated hardware and runs on an off-the-shelf iPhone. It fuses together synchronized RGB, IMU, Lidar-guided depth, and 6-DoF pose out of the box from ARKit and exports them to a raw MCAP file.
Dataset: fpvlabs/stera-10m
Launch Details: https://x.com/fpv_labs/status/2055262652033908832
We're releasing Stera, an open-source infra that turns an off-the-shelf device in your pocket into a high-fidelity multimodal data pipeline. It's built around four layers. Capture โ Process โ Evaluate โ Export.
Stera Capture removes the need for bespoke/gated hardware and runs on an off-the-shelf iPhone. It fuses together synchronized RGB, IMU, Lidar-guided depth, and 6-DoF pose out of the box from ARKit and exports them to a raw MCAP file.
Dataset: fpvlabs/stera-10m
Launch Details: https://x.com/fpv_labs/status/2055262652033908832
Post
6195
Want to share my enthusiasm for zai-org/GLM-5.1 here too ๐ฅ
I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:
- One-shot car physics with real drift mechanics (this is hard)
- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen
- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters
- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!
- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed
You are going to hear about this model a lot in the next months - open source let's go - and thanks z-ai๐๐
I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:
- One-shot car physics with real drift mechanics (this is hard)
- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen
- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters
- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!
- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed
You are going to hear about this model a lot in the next months - open source let's go - and thanks z-ai๐๐
- 5 replies
Post
190
OpenAI is hiring for SLAM Engineers!
And open-source shouldn't lag behind.
It's pretty hard and necessary problem required to be solved for bringing generalisable robots in real-world.
We are pushing out first deep down & will be open-sourcing stuff in the next releases. Hope everyone is ready! Cheers to HF & more hugs.
Find us at https://x.com/fpv_labs/status/2042585804162371713
And open-source shouldn't lag behind.
It's pretty hard and necessary problem required to be solved for bringing generalisable robots in real-world.
We are pushing out first deep down & will be open-sourcing stuff in the next releases. Hope everyone is ready! Cheers to HF & more hugs.
Find us at https://x.com/fpv_labs/status/2042585804162371713
xianbaoย
submitted a
paper to Daily Papers 4 months ago
victorย
submitted a
paper to Daily Papers 4 months ago
chansungย
authored a
paper 5 months ago
chansungย
submitted a
paper to Daily Papers 5 months ago
Post
2838
Interesting article: use Claude Code to help open models write CUDA kernels (for eg) by turning CC traces into Skills. They made a library out of it ๐
https://huggingface.co/blog/upskill
https://huggingface.co/blog/upskill
Post
3577
Nvidia is on a roll lately. Nemotron 3 Nano is my new fav local model, but here's the real flex: they published the entire evaluation setup. Configs, prompts, logs, all of it. This is how you do open models ๐ฅ
https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
mrfakenameย
posted an update 7 months ago
Post
27733
Excited to share that I've joined the Hugging Face Fellows program! ๐ค
Looking forward to contributing to & working more closely with the open-source ecosystem - huge thanks to everyone who's supported me on this journey! ๐
Looking forward to contributing to & working more closely with the open-source ecosystem - huge thanks to everyone who's supported me on this journey! ๐
xianbaoย
authored a
paper 8 months ago
nouamanetaziย
posted an update 8 months ago
Post
4992
After training ๐๐ฆ๐จ๐ฅ๐๐๐ on ๐๐๐ ๐๐๐๐๐ฌ for nearly a month, I've come to realize something most people overlook: ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ข๐ฌ ๐ญ๐ก๐ ๐ฆ๐๐ค๐-๐จ๐ซ-๐๐ซ๐๐๐ค ๐๐๐๐ญ๐จ๐ซ ๐ข๐ง ๐๐๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ . ๐ฅ
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team
mrfakenameย
posted an update 9 months ago
Post
6472
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
osansevieroย
authored a
paper 10 months ago
davanstrienย
posted an update 10 months ago
Post
2992
I fine-tuned a smol VLM to generate specialized art history metadata!
https://huggingface.co/davanstrien/iconclass-vlm: Qwen2.5-VL-3B trained using SFT to generate ICONCLASS codes (think Dewey Decimal for art!)
Trained with TRL + HF Jobs - single UV script, no GPU needed!
Space to explore predictions on a test set: davanstrien/iconclass-predictions
Blog soon!
https://huggingface.co/davanstrien/iconclass-vlm: Qwen2.5-VL-3B trained using SFT to generate ICONCLASS codes (think Dewey Decimal for art!)
Trained with TRL + HF Jobs - single UV script, no GPU needed!
Space to explore predictions on a test set: davanstrien/iconclass-predictions
Blog soon!
- 1 reply