Join the conversation
Join the community of Machine Learners and AI enthusiasts.
Sign UpAll HF Hub posts
hesamation
posted an update
about 17 hours ago
Post
1177
Google published a 69-page whitepaper on Prompt Engineering and its best practices, a must-read if you are using LLMs in production:
> zero-shot, one-shot, few-shot
> system prompting
> chain-of-thought (CoT)
> ReAct
LINK: https://www.kaggle.com/whitepaper-prompt-engineering
> code prompting
> best practices
> zero-shot, one-shot, few-shot
> system prompting
> chain-of-thought (CoT)
> ReAct
LINK: https://www.kaggle.com/whitepaper-prompt-engineering
> code prompting
> best practices
Post
1157
🎨 Designers, meet OmniSVG! This new model helps you create professional vector graphics from text/images, generate editable SVGs from icons to detailed characters, convert rasters to vectors, maintain style consistency with references, and integrate into your workflow.
@OmniSVG
@OmniSVG
- 1 reply
danielhanchen
posted an update
2 days ago
Post
3966
You can now run Llama 4 on your own local device! 🦙
Run our Dynamic 1.78-bit and 2.71-bit Llama 4 GGUFs:
unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
You can run them on llama.cpp and other inference engines. See our guide here: https://docs.unsloth.ai/basics/tutorial-how-to-run-and-fine-tune-llama-4
Run our Dynamic 1.78-bit and 2.71-bit Llama 4 GGUFs:
unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
You can run them on llama.cpp and other inference engines. See our guide here: https://docs.unsloth.ai/basics/tutorial-how-to-run-and-fine-tune-llama-4
- 1 reply
jasoncorkill
posted an update
1 day ago
Post
1617
🔥 Yesterday was a fire day!
We dropped two brand-new datasets capturing Human Preferences for text-to-video and text-to-image generations powered by our own crowdsourcing tool!
Whether you're working on model evaluation, alignment, or fine-tuning, this is for you.
1. Text-to-Video Dataset (Pika 2.2 model):
Rapidata/text-2-video-human-preferences-pika2.2
2. Text-to-Image Dataset (Reve-AI Halfmoon):
Rapidata/Reve-AI-Halfmoon_t2i_human_preference
Let’s train AI on AI-generated content with humans in the loop.
Let’s make generative models that actually get us.
We dropped two brand-new datasets capturing Human Preferences for text-to-video and text-to-image generations powered by our own crowdsourcing tool!
Whether you're working on model evaluation, alignment, or fine-tuning, this is for you.
1. Text-to-Video Dataset (Pika 2.2 model):
Rapidata/text-2-video-human-preferences-pika2.2
2. Text-to-Image Dataset (Reve-AI Halfmoon):
Rapidata/Reve-AI-Halfmoon_t2i_human_preference
Let’s train AI on AI-generated content with humans in the loop.
Let’s make generative models that actually get us.
Post
2227
🎉 GitHub selected the ultralytics computer vision project, known for its YOLOv8/YOLO11 real-time SOTA computer vision models, as one of the top 5 open-source projects for first-time contributors in 2024!
Link to the project: https://github.com/ultralytics/ultralytics
Link to the full GitHub 2024 recap report: https://github.blog/news-insights/octoverse/octoverse-2024/
Link to the project: https://github.com/ultralytics/ultralytics
Link to the full GitHub 2024 recap report: https://github.blog/news-insights/octoverse/octoverse-2024/
- 2 replies
ajibawa-2023
posted an update
about 10 hours ago
Post
1112
Hi All, I recently released two Audio datasets which are generated using my earlier released dataset:
ajibawa-2023/Children-Stories-Collection
First Audio Dataset:https://huggingface.co/datasets/ajibawa-2023/Audio-Children-Stories-Collection-Large has 5600++ stories in .mp3 format.
Second Audio Dataset:https://huggingface.co/datasets/ajibawa-2023/Audio-Children-Stories-Collection has 600 stories in .mp3 format.
First Audio Dataset:https://huggingface.co/datasets/ajibawa-2023/Audio-Children-Stories-Collection-Large has 5600++ stories in .mp3 format.
Second Audio Dataset:https://huggingface.co/datasets/ajibawa-2023/Audio-Children-Stories-Collection has 600 stories in .mp3 format.
-
- 3 replies
Steven10429
posted an update
1 day ago
Post
1837
I got rejected from llama4.
So that means I can use quantinized model without following their TOS.
Interesting.
So that means I can use quantinized model without following their TOS.
Interesting.
- 3 replies
Post
2414
What does it mean when models share the same bytes?
We've investigated some quants and have seen that a considerable portion of quantizations of the same model share the same bytes and can be deduplicated to save considerable upload time for quantizers on the Hub.
This space where we crack open a repo from @bartowski shows we can get significant dedupe xet-team/quantization-dedup
You can get a sense of why by reading this write-up: https://github.com/bartowski1182/llm-knowledge/blob/main/quantization/quantization.md
But what about finetuned models?
Since going into production the
xet-team
has migrated hundreds of repositories on the Hub to our storage layer, including classic "pre-Hub" open-source models like
FacebookAI/xlm-roberta-large (XLM-R) from
FacebookAI
XLM-R, introduced in 2019, set new benchmarks for multilingual NLP by learning shared representations across 100 languages. It was then fine-tuned on English, Spanish, Dutch, and German, generating language-specific derivations for each - check out the paper here Unsupervised Cross-lingual Representation Learning at Scale (1911.02116)
These finetunes share much of the same architecture and layout as XLM-R with similar training methods and goals. It makes sense that they would share bytes, but it's still fascinating to see.
We put together a similar space to explore these models to see where they overlap - check it out for yourself xet-team/finetune-dedupe
The darker each block in the heatmap, the more the bytes are shared. Clicking on a repos blocks shows all other repos that share blocks.
We've investigated some quants and have seen that a considerable portion of quantizations of the same model share the same bytes and can be deduplicated to save considerable upload time for quantizers on the Hub.
This space where we crack open a repo from @bartowski shows we can get significant dedupe xet-team/quantization-dedup
You can get a sense of why by reading this write-up: https://github.com/bartowski1182/llm-knowledge/blob/main/quantization/quantization.md
But what about finetuned models?
Since going into production the
xet-team
has migrated hundreds of repositories on the Hub to our storage layer, including classic "pre-Hub" open-source models like
FacebookAI/xlm-roberta-large (XLM-R) from
FacebookAI
XLM-R, introduced in 2019, set new benchmarks for multilingual NLP by learning shared representations across 100 languages. It was then fine-tuned on English, Spanish, Dutch, and German, generating language-specific derivations for each - check out the paper here Unsupervised Cross-lingual Representation Learning at Scale (1911.02116)
These finetunes share much of the same architecture and layout as XLM-R with similar training methods and goals. It makes sense that they would share bytes, but it's still fascinating to see.
We put together a similar space to explore these models to see where they overlap - check it out for yourself xet-team/finetune-dedupe
The darker each block in the heatmap, the more the bytes are shared. Clicking on a repos blocks shows all other repos that share blocks.
- 1 reply
Post
2271
New in PawMatchAI🐾 : Turn Your Dog Photos into Art!
I’m excited to introduce a brand-new creative feature — Dog Style Transfer is now live on PawMatchAI!
Just upload your dog’s photo and transform it into 5 artistic styles:
🌸 Japanese Anime
📚 Classic Cartoon
🖼️ Oil Painting
🎨 Watercolor
🌆 Cyberpunk
All powered by Stable Diffusion and enhanced with smart prompt tuning to preserve your dog’s unique traits and breed identity , so the artwork stays true to your furry friend.
Whether you're creating a custom portrait or just having fun, this feature brings your pet photos to life in completely new ways.
And here’s a little secret: although it’s designed with dogs in mind, it actually works on any photo — cats, plush toys, even humans. Feel free to experiment!
Results may not always be perfectly accurate, sometimes your photo might come back looking a little different, or even beyond your imagination. But that’s part of the fun! It’s all about creative surprises and letting the AI do its thing.
Try it now: DawnC/PawMatchAI
If this new feature made you smile, a ❤️ for this space would mean a lot.
#AIArt #StyleTransfer #StableDiffusion #ComputerVision #MachineLearning #DeepLearning
I’m excited to introduce a brand-new creative feature — Dog Style Transfer is now live on PawMatchAI!
Just upload your dog’s photo and transform it into 5 artistic styles:
🌸 Japanese Anime
📚 Classic Cartoon
🖼️ Oil Painting
🎨 Watercolor
🌆 Cyberpunk
All powered by Stable Diffusion and enhanced with smart prompt tuning to preserve your dog’s unique traits and breed identity , so the artwork stays true to your furry friend.
Whether you're creating a custom portrait or just having fun, this feature brings your pet photos to life in completely new ways.
And here’s a little secret: although it’s designed with dogs in mind, it actually works on any photo — cats, plush toys, even humans. Feel free to experiment!
Results may not always be perfectly accurate, sometimes your photo might come back looking a little different, or even beyond your imagination. But that’s part of the fun! It’s all about creative surprises and letting the AI do its thing.
Try it now: DawnC/PawMatchAI
If this new feature made you smile, a ❤️ for this space would mean a lot.
#AIArt #StyleTransfer #StableDiffusion #ComputerVision #MachineLearning #DeepLearning
