Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts

openfreeย 
posted an update about 21 hours ago
view post
Post
1994
๐Ÿธ Pepe Meme Generator

Hello to everyone who loves frog memes! Now you can generate fun images of Pepe in various scenarios. By using the DiffusionPipeline from Hugging Face and LoRA (a method of adding additional training data to a large model for a specific style), you can easily create Pepe characters.

๐Ÿ€ Model & Space Links
Model Link:
openfree/pepe

Space Link:
openfree/pepe

The model card includes LoRA weights related to the Pepe character, allowing you to easily create meme-style images.
On the Space page, you can generate Pepe images right away via the web UI without writing extra code!

โญ Main Features
Meme-Style Pepe Images

Enter prompts like โ€œPepe dancing excitedlyโ€ or โ€œPepe busking in the streets of New York,โ€ and it automatically generates an image.
From comical, cartoon-like memes to a somewhat serious(?) Pepe, you can achieve a wide variety of styles.
LoRA Scale Adjustment

Change the LoRA scale parameter to fine-tune how strongly the Pepe style is applied.
A value closer to 0 yields a more generic image, while a value closer to 1 results in a strongly cartoon-like Pepe appearance.
Advanced Settings

Modify the Height and Width to generate vertical or horizontal images of different aspect ratios.
Adjust Guidance scale and Inference steps to get the exact level of detail and artistic style you want.
Seed Configuration

Choose a fixed seed or a random seed so that images are either reproducible or new every time.
๐Ÿš€ Usage Ideas
SNS Meme Creation

Quickly make fun Pepe images for Twitter or Instagram Stories.
Perfect for events, birthdays, or any special occasion memes!
Fan Art & Merch Design

Use generated images as references for Pepe fan art, or draft designs for merchandise (stickers, T-shirts, etc.).
Blog & Community Posts

Spice up your blog articles or community posts with meme images.
Set up humorous scenarios featuring Pepe as an entertaining โ€œreaction image.โ€
merveย 
posted an update about 3 hours ago
view post
Post
264
Oof, what a week! ๐Ÿฅต So many things have happened, let's recap! merve/jan-24-releases-6793d610774073328eac67a9

Multimodal ๐Ÿ’ฌ
- We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG ๐Ÿ’—
- UI-TARS are new models by ByteDance to unlock agentic GUI control ๐Ÿคฏ in 2B, 7B and 72B
- Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B
- MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context
- Dataset: Yale released a new benchmark called MMVU
- Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark

LLMs ๐Ÿ“–
- DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! ๐Ÿคฏ
- Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B
- NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!)

Audio ๐Ÿ—ฃ๏ธ
- Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B
- TangoFlux is a new audio generation model trained from scratch and aligned with CRPO

Image/Video/3D Generation โฏ๏ธ
- Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux
- tencent released Hunyuan3D-2, new 3D asset generation from images
ยท
burtenshawย 
posted an update 1 day ago
view post
Post
1106
AI was built on side projects!
AdinaYย 
posted an update 2 days ago
sometimesanotionย 
posted an update 2 days ago
view post
Post
2255
I've managed a #1 score of 41.22% average for 14B parameter models on the Open LLM Leaderboard. As of this writing, sometimesanotion/Lamarck-14B-v0.7 is #8 for all models up to 70B parameters.

It took a custom toolchain around Arcee AI's mergekit to manage the complex merges, gradients, and LoRAs required to make this happen. I really like seeing features of many quality finetunes in one solid generalist model.
ยท
m-ricย 
posted an update about 7 hours ago
view post
Post
329
Today we make the biggest release in smolagents so far: ๐˜„๐—ฒ ๐—ฒ๐—ป๐—ฎ๐—ฏ๐—น๐—ฒ ๐˜ƒ๐—ถ๐˜€๐—ถ๐—ผ๐—ป ๐—บ๐—ผ๐—ฑ๐—ฒ๐—น๐˜€, ๐˜„๐—ต๐—ถ๐—ฐ๐—ต ๐—ฎ๐—น๐—น๐—ผ๐˜„๐˜€ ๐˜๐—ผ ๐—ฏ๐˜‚๐—ถ๐—น๐—ฑ ๐—ฝ๐—ผ๐˜„๐—ฒ๐—ฟ๐—ณ๐˜‚๐—น ๐˜„๐—ฒ๐—ฏ ๐—ฏ๐—ฟ๐—ผ๐˜„๐˜€๐—ถ๐—ป๐—ด ๐—ฎ๐—ด๐—ฒ๐—ป๐˜๐˜€! ๐Ÿฅณ

Our agents can now casually open up a web browser, and navigate on it by scrolling, clicking elements on the webpage, going back, just like a user would.

The demo below shows Claude-3.5-Sonnet browsing GitHub for task: "Find how many commits the author of the current top trending repo did over last year."
Hi @mlabonne !

Go try it out, it's the most cracked agentic stuff I've seen in a while ๐Ÿคฏ (well, along with OpenAI's Operator who beat us by one day)

For more detail, read our announcement blog ๐Ÿ‘‰ https://huggingface.co./blog/smolagents-can-see
The code for the web browser example is here ๐Ÿ‘‰ https://github.com/huggingface/smolagents/blob/main/examples/vlm_web_browser.py
  • 1 reply
ยท
singhsidhukuldeepย 
posted an update 3 days ago
view post
Post
2778
Exciting breakthrough in Retrieval-Augmented Generation (RAG): Introducing MiniRAG - a revolutionary approach that makes RAG systems accessible for edge devices and resource-constrained environments.

Key innovations that set MiniRAG apart:

Semantic-aware Heterogeneous Graph Indexing
- Combines text chunks and named entities in a unified structure
- Reduces reliance on complex semantic understanding
- Creates rich semantic networks for precise information retrieval

Lightweight Topology-Enhanced Retrieval
- Leverages graph structures for efficient knowledge discovery
- Uses pattern matching and localized text processing
- Implements query-guided reasoning path discovery

Impressive Performance Metrics
- Achieves comparable results to LLM-based methods while using Small Language Models (SLMs)
- Requires only 25% of storage space compared to existing solutions
- Maintains robust performance with accuracy reduction ranging from just 0.8% to 20%

The researchers from Hong Kong University have also contributed a comprehensive benchmark dataset specifically designed for evaluating lightweight RAG systems under realistic on-device scenarios.

This breakthrough opens new possibilities for:
- Edge device AI applications
- Privacy-sensitive implementations
- Real-time processing systems
- Resource-constrained environments

The full implementation and datasets are available on GitHub: HKUDS/MiniRAG
  • 1 reply
ยท
burtenshawย 
posted an update 3 days ago
view post
Post
3241
๐Ÿšง Work in Progress! ๐Ÿšง

๐Ÿ‘ทโ€โ™€๏ธ We're working hard on getting the official agents course ready for the 50,000 students that have signed up.

If you want to contribute to the discussion, I started these community posts. Looking forward to hearing from you:

- smolagents unit in the agents course - agents-course/README#7
- LlamaIndex Unit in the agents course - agents-course/README#6
- LangChain and LangGraph unit in the agents course - agents-course/README#5
- Real world use cases in the agents course - agents-course/README#8


chansungย 
posted an update 1 day ago
view post
Post
1090
New look for AI powered paper reviews from the list by Hugging Face Daily Papers ( managed by the @akhaliq )

Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.

Link: https://deep-diver.github.io/ai-paper-reviewer/

This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)
sharpenbย 
posted an update 2 days ago