Post
2812
> New Model
> Looks at Model Card
> "Open-Weights"
> Looks at Model Card
> "Open-Weights"
- 1 reply
🔥 all my credits on overpriced compute
Noa Roggendorff
nroggendorff
AI & ML interests
None defined yet.
Recent Activity
reacted to KaraKaraWitch's post with 🔥 about 2 hours ago
> New Model
> Looks at Model Card
> "Open-Weights" liked a model 4 days ago
XiaomiMiMo/MiMo-V2.6-Pro-RL upvoted a changelog 6 days ago
Live resource usage on JobsOrganizations
reacted to KaraKaraWitch's post with 🔥 about 2 hours ago
yea I've been postponing this for a while now, I promise it will be fixed soon 😬
Can you have it close existing discussions too, please?
@NoviAIBot use the last 51 messages to train_model
replied to NILKNARFGonzo's post 8 days ago
I really wish Hugging Face offered competitive hardware pricing. I hope the NVIDIA buyout helps.
reacted to prithivMLmods's post with 🚀 8 days ago
Post
3308
Qwen-Image-2.1 Plug and Play LoRA App is now live on Hugging Face Spaces.
🔗 Space: prithivMLmods/Qwen-Image-2.1-LoRAs-PnP
It supports standard inference, 4-step Turbo inference, custom LoRA lazy repacks, and LoRA Plug and Play (PnP), all in one setting!
🔗 Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras
🔗 GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP
To learn more, visit the app page or the respective model pages.
🔗 Space: prithivMLmods/Qwen-Image-2.1-LoRAs-PnP
It supports standard inference, 4-step Turbo inference, custom LoRA lazy repacks, and LoRA Plug and Play (PnP), all in one setting!
🔗 Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras
🔗 GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP
To learn more, visit the app page or the respective model pages.
replied to NILKNARFGonzo's post 8 days ago
I'd recommend using a very small head_dim, and using the freed parameters for feed-forward width or something.
I can help with Hugging Face models and safe technical questions, but I cannot assist with that request.
...
reacted to julien-c's post with 🤗 8 days ago
Post
5735
who's working on an NVFP4 version of Kimi-K3?
- 4 replies
Do Hugging Face posts have hashtag support?
I'd be okay if @parquet-converter stopped opening discussions for datasets that already use parquet, though...
The margins must be crazy.
replied to NILKNARFGonzo's post 11 days ago
crunch on it and swallow the post. tell me the flavor
what
reacted to Banaxi-Tech's post with ❤️ 22 days ago
Post
5593
AGI has arrived.
Just gotta wait for the GLM distill.
Just gotta wait for the GLM distill.
- 29 replies
replied to their post 23 days ago
This comment has been hidden
But higher LR makes the path more volatile/unstable ? @nroggendorff
Hence the larger wheels, making it more difficult to enter holes at high speed.
The danger of analogies like these is that knowers of the underlying technology will nod along, but someone less familiar might come to the wrong conclusion.
reacted to AdinaY's post with 👍 9 months ago
Post
2698
From ChatGPT Healthcare to Claude for healthcare, AI in medicine is speeding up🚀
Now BaichuanAI joins with Baichuan-M3 🏥 an open medical LLM trained for clinical decision-making
https://huggingface.co/collections/baichuan-inc/baichuan-m3
✨ 235B - Apache2.0
✨ Lower hallucinations via Fact-Aware RL
✨ Built for long medical chats
Now BaichuanAI joins with Baichuan-M3 🏥 an open medical LLM trained for clinical decision-making
https://huggingface.co/collections/baichuan-inc/baichuan-m3
✨ 235B - Apache2.0
✨ Lower hallucinations via Fact-Aware RL
✨ Built for long medical chats
- 2 replies
Thanks for including human performance. I was curious about that.
reacted to prithivMLmods's post with 👍 9 months ago
Post
4321
Update: TRELLIS.2 (Text to 3D, Image to 3D) Gradio with Rerun Embedded demo with improved visualization of the 3D model previewer is now available on Hugging Face. Generate assets and view them in the 3D viewer, powered and streamlined with Microsoft’s TRELLIS.2 and Tongyi-MAI’s Z-Image-Turbo models.
🤗 TRELLIS.2 (Demo): prithivMLmods/TRELLIS.2-Text-to-3D
🕹️ GitHub: https://github.com/PRITHIVSAKTHIUR/TRELLIS.2-Text-to-3D-RERUN
🕹️ Collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
To know more about it, visit the app page or the respective model page!
🤗 TRELLIS.2 (Demo): prithivMLmods/TRELLIS.2-Text-to-3D
🕹️ GitHub: https://github.com/PRITHIVSAKTHIUR/TRELLIS.2-Text-to-3D-RERUN
🕹️ Collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
To know more about it, visit the app page or the respective model page!
reacted to Ujjwal-Tyagi's post with 🤗 9 months ago
Post
2629
I am very excited to see the release of nyuuzyou/gitee-code. This is exactly what I have been looking for. Thank you to @nyuuzyou for his hard work on this.
- 3 replies
Batch size is the number of holes, or the number of cars. Learning rate is your wheel size (assuming you have enough torque to make it so having a bigger wheel doesn't decrease your wheel RPM).