John6666 (John Smith)

Reacted to nyuuzyou's post with 🤗 about 16 hours ago

Post

347

Hugging Face recently added Bluesky to profile links, which is cool. It would be great to also support links to alternative Git services like Codeberg, GitLab, and Gitea. Many developers use platforms beyond GitHub, and showcasing repositories from these sites would be a great feature

Reacted to nataliaElv's post with 👀 about 16 hours ago

Post

536

Would you like to get a high-quality dataset to pre-train LLMs in your language? 🌏

At Hugging Face we're preparing a collaborative annotation effort to build an open-source multilingual dataset as part of the Data is Better Together initiative.

Follow the link below, check if your language is listed and sign up to be a Language Lead!

https://forms.gle/s9nGajBh6Pb9G72J6

Reacted to as-cle-bert's post with 🤗 about 22 hours ago

Post

581

Hi there!🤗

I just deployed a Streamlit-based space on HF that fetches your Home Feed on BlueSky and summarizes it with Cohere's CommandR via Langchain🧪

Find it here:
as-cle-bert/bsky-feedllama-demo

I'm also working on a Gradio local implementation with Llama3.2 that for now only works with source code and doesn't have docs, but that will be soon supported by Docker🐳 and have a nice README:

https://github.com/AstraBert/bluesky-feedllama

Contributions and feedback are always welcome!🤗🦋

Reacted to mikelabs's post with 👍 about 22 hours ago

Post

646

LLMs developing theory of mind is wild - were basically teaching AI to understand what other AIs are thinking. Its like robot therapy but for making them better team players 🤖🧠

https://www.aimodels.fyi/papers/arxiv/large-model-strategic-thinking-small-model-efficiency

Reacted to xiaozaa's post with 🔥 about 22 hours ago

Post

769

Hey everyone! 👋 Just launched a cool virtual try-on demo on Hugging Face Spaces! 🚀
Try on any upper body garment with just 3 simple steps:
📸 Upload your photo
✏️ Draw a quick mask
👕 Add the garment image
Super accurate results and really easy to use! Give it a spin and let me know what you think 🤗

Find here:
xiaozaa/catvton-flux-try-on

Reacted to LukeNeumann's post with 👀 about 22 hours ago

Post

644

I had a question about Trending datasets. Our initial dataset "Oregon Coast in 4K" was trending at #3 for video at about 700 downloads.

Over the past two days our downloads have spiked, now up to over 2,000, but the dataset has dropped down to the 3rd or 4th page of Trending.

What metrics are used to determine dataset Trending position?

1 reply

·

Reacted to MonsterMMORPG's post with 👀 about 22 hours ago

Post

902

FLUX Redux is a hidden Gem

I am still doing huge research to publish an amazing fully Public - no paywalled Tutorial, but this is generated via SwarmUI

Style Model Merge Strength : 0.5

FLUX Guidance Scale is : 6

Used base model is my FLUX fine tuned model with 256 images via Kohya SS GUI as shown in tutorial ( https://youtu.be/FvpWy1x5etM ) - 70 epoch

Prompt : anime ohwx man walking in a jungle <segment:yolo-face_yolov9c.pt-1,0.7,0.5> ohwx man, anime

2 replies

·

Reacted to appliedml42's post with 👀 about 22 hours ago

Post

889

I am trying to find resources that explain how I can protect against instruction following capability degradation due to LoRA fine-tuning.

For example, I fine-tuned Llama 3.2 3B Instruct on cornell-movie-review-data/rotten_tomatoes dataset and saw significant degradation in ifeval benchmark scores.

I would appreciate any pointers 🙏🏽

Reacted to davidberenstein1957's post with 🔥 1 day ago

Post

1240

Let’s make a generation of amazing image-generation models

The best image generation models are trained on human preference datasets, where annotators have selected the best image from a choice of two. Unfortunately, many of these datasets are closed source so the community cannot train open models on them. Let’s change that!

The community can contribute image preferences for an open-source dataset that could be used for building AI models that convert text to image, like the flux or stable diffusion families. The dataset will be open source so everyone can use it to train models that we can all use.

Blog: https://huggingface.co/blog/burtenshaw/image-preferences

Reacted to KnutJaegersberg's post with 🔥 1 day ago

Post

839

openGPT-X/Teuken-7B-instruct-research-v0.4

New European LLM

openGPT-X/Teuken-7B-instruct-research-v0.4

Reacted to luigi12345's post with 👀 1 day ago

Post

195

Top 20 GitHub Repositories for Autonomous AI Agents in Software Development

Best AI Software Engineer Agents and AI Frameworks and Tools.
Discover the top 20 GitHub repositories for autonomous AI agents in software development. These tools offer features like automated testing, debugging, and codebase management, complete with user-friendly interfaces. Enhance your development workflow with these cutting-edge resources. Read more: https://huggingface.co/blog/luigi12345/ai-autonomous-agents

Reacted to davanstrien's post with ❤️ 1 day ago

Post

1461

First dataset for the new Hugging Face Bluesky community organisation: bluesky-community/one-million-bluesky-posts 🦋

📊 1M public posts from Bluesky's firehose API
🔍 Includes text, metadata, and language predictions
🔬 Perfect to experiment with using ML for Bluesky 🤗

Excited to see people build more open tools for a more open social media platform!

Reacted to anakin87's post with 👀 1 day ago

Post

232

🐝🐝🐝 𝐀 𝐒𝐰𝐚𝐫𝐦 𝐨𝐟 𝐀𝐠𝐞𝐧𝐭𝐬 𝐰𝐢𝐭𝐡 𝐋𝐥𝐚𝐦𝐚 3.2, 𝐆𝐏𝐓-4𝐨 𝐦𝐢𝐧𝐢 𝐚𝐧𝐝 𝐂𝐥𝐚𝐮𝐝𝐞 3.5 𝐒𝐨𝐧𝐧𝐞𝐭

𝐓𝐋;𝐃𝐑: I reimplemented the Swarm concept using Haystack, but made it work with both open and proprietary models 💫

✍️ blog article: https://haystack.deepset.ai/blog/swarm-of-agents
📓 notebook: https://haystack.deepset.ai/cookbook/swarm

Some time ago OpenAI published Swarm: an educational framework for building multi-agent systems.

Their approach focuses on two main concepts:
・ 𝐑𝐨𝐮𝐭𝐢𝐧𝐞𝐬: Each agent follows specific 📜 instructions and uses 🛠️ tools to execute them.
・ 𝐇𝐚𝐧𝐝𝐨𝐟𝐟𝐬 🤝: Agents can transfer control to one another using tool/function calling.

When I first read these ideas, I thought: 𝘴𝘪𝘮𝘱𝘭𝘦 𝘣𝘶𝘵 𝘱𝘰𝘸𝘦𝘳𝘧𝘶𝘭! And they pair well with the recent unified tool support in Haystack.

🧑‍💻 So, I decided to re-implement these concepts using Haystack, and in just a few lines of code, I had a working prototype.

🆒 Bonus feature: this implementation isn't tied to a single model provider - different agents can be powered by different models!

I replicated the ACME customer service example from the original article, with 3 Agents:
🐝 Triage Agent - Llama 3.2 running on Ollama
🐝 Sales Agent - Anthropic Claude 3.5 Sonnet
🐝 Issues and Repairs Agent - OpenAI GPT-4o mini

Want to see the full implementation and give it a try? Check out the blog post and notebook! ✨

Reacted to vilarin's post with 🔥 1 day ago

Post

942

A few days ago, Blackforestlabs released FLUX.1 Tools, which has surprised everyone with its quality and effects. Now that diffusers support these features, you can easily deploy and build your own Tools.
Combined with the powerful Gradio and ZeroGPU, you can experience the Tools immediately, which is truly wonderful.
I was impressed by the Flux.1 Fill dev, so here I've built a demo for it, making it easy to use for inpainting and outpainting images.

🏄Model: black-forest-labs/FLUX.1-Fill-dev
🦖Demo: vilarin/Flux.1-Fill-dev
👏diffusers: https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines/flux

Reacted to vansin's post with 👀 1 day ago

Post

911

Amazing !!!! test Post

Reacted to jsulz's post with 👀 1 day ago

Post

946

Something I love about working at Hugging Face is the opportunity to design and work in public. Right now, we’re redesigning the architecture that supports uploads and downloads on the Hub.

Datasets and models are growing fast, and so are the challenges of storing and transferring them efficiently. To keep up, we're introducing a new protocol for uploads and downloads, supported by a content-addressed store (CAS).

Here’s what’s coming:

📦 Smarter uploads: Chunk-level management enables advanced deduplication, compression, and reduces redundant transfers, speeding up uploads.
⚡ Efficient downloads: High throughput and low latency ensure fast access, even during high-demand model releases.
🔒 Enhanced security: Validate uploads before storage to block malicious or invalid data.

We analyzed 24 hours of global upload activity in October (88 countries, 130TB of data!) to design a system that scales with your needs.

The result? A proposed infrastructure with CAS nodes in us-east-1, eu-west-3, and ap-southeast-1.

🔗 Read the blog post for the full details: https://huggingface.co/blog/rearchitecting-uploads-and-downloads

🌟 Check out our interactive demo to explore the data yourself!
xet-team/cas-analysis

We’d love to hear your feedback - let us know if you have questions or want to see more.

5 replies

·

Reacted to merve's post with 🤗🔥 1 day ago

Post

2202

Small yet mighty! 💫

We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient 🤠

We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39

Learn more from our blog here: huggingface.co/blog/smolvlm
This release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO 💝
Try the demo: HuggingFaceTB/SmolVLM
Fine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Also TRL integration for DPO 💗

Reacted to maxiw's post with 🚀 2 days ago

Post

1690

You can now try out computer use models from the hub to automate your local machine with https://github.com/askui/vision-agent. 💻

import time
from askui import VisionAgent

with VisionAgent() as agent:
    agent.tools.webbrowser.open_new("http://www.google.com")
    time.sleep(0.5)
    agent.click("search field in the center of the screen", model_name="Qwen/Qwen2-VL-7B-Instruct")
    agent.type("cats")
    agent.keyboard("enter")
    time.sleep(0.5)
    agent.click("text 'Images'", model_name="AskUI/PTA-1")
    time.sleep(0.5)
    agent.click("second cat image", model_name="OS-Copilot/OS-Atlas-Base-7B")

Currently these models are integrated with Gradio Spaces API. Also planning to add local inference soon!

Currently supported:
- Qwen/Qwen2-VL-7B-Instruct
- Qwen/Qwen2-VL-2B-Instruct
- AskUI/PTA-1
- OS-Copilot/OS-Atlas-Base-7B

2 replies

·

Reacted to csabakecskemeti's post with 👀 2 days ago

Post

1047

I have this small utility: no_more_typo
It is running in the background and able to call the LLM model to update the text on the clipboard. I think it would be ideal to fix typos and syntax.
I have just added the option to use custom prompt templates to perform different tasks.

Details, code and executable:
https://github.com/csabakecskemeti/no_more_typo

https://devquasar.com/no-more-typo/

John Smith PRO

AI & ML interests

Recent Activity

Organizations

John6666's activity