John6666 (John Smith)

reacted to as-cle-bert's post with 👍 about 7 hours ago

Post

284

Hey there, 𝗶𝗻𝗴𝗲𝘀𝘁-𝗮𝗻𝘆𝘁𝗵𝗶𝗻𝗴 𝘃𝟭.𝟬.𝟬 just dropped with major changes:

✅ Embeddings: now works with Sentence Transformers, Jina AI, Cohere, OpenAI, and Model2Vec
All powered via 𝗖𝗵𝗼𝗻𝗸𝗶𝗲’𝘀 𝗔𝘂𝘁𝗼𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀.
No more local-only limitations 🙌
✅ Vector DBs: now supports 𝗮𝗹𝗹 𝗟𝗹𝗮𝗺𝗮𝗜𝗻𝗱𝗲𝘅-𝗰𝗼𝗺𝗽𝗮𝘁𝗶𝗯𝗹𝗲 𝗯𝗮𝗰𝗸𝗲𝗻𝗱𝘀
Think: Qdrant, Pinecone, Weaviate, Milvus, etc.
No more bottlenecks🔓
✅ File parsing: now plugs into any 𝗟𝗹𝗮𝗺𝗮𝗜𝗻𝗱𝗲𝘅-𝗰𝗼𝗺𝗽𝗮𝘁𝗶𝗯𝗹𝗲 𝗱𝗮𝘁𝗮 𝗹𝗼𝗮𝗱𝗲𝗿
Using LlamaParse, Docling or your own setup? You’re covered.
Curious of knowing more? Try it out! 👉 https://github.com/AstraBert/ingest-anything

reacted to ProCreations's post with 👀 about 7 hours ago

Post

372

🧠 Post of the Day: Quantum AI – Your Thoughts + Our Take

Yesterday we asked: “What will quantum computing do to AI?”
Big thanks to solongeran for this poetic insight:

“Quantum computers are hard to run error-free. But once they’re reliable, AI will be there. Safer than the daily sunset. Shure – no more queues ;)”

🚀 Our Take – What Quantum Computing Will Do to AI (by 2035)

By the time scalable, fault-tolerant quantum computers arrive, AI won’t just run faster — it’ll evolve in ways we’ve never seen:

⸻

🔹 1. Huge Speedups in Optimization & Search
Why: Quantum algorithms like Grover’s can cut down search and optimization times exponentially in some cases.
How: They’ll power up tasks like hyperparameter tuning, decision-making in RL, and neural architecture search — crunching what now takes hours into seconds.

⸻

🔹 2. Quantum Neural Networks (QNNs)
Why: QNNs can represent complex relationships more efficiently than classical nets.
How: They use entanglement and superposition to model rich feature spaces, especially useful for messy or high-dimensional data — think drug discovery, finance, or even language structure.

⸻

🔹 3. Autonomous Scientific Discovery
Why: Quantum AI could simulate molecular systems that are impossible for classical computers.
How: By combining quantum simulation with AI exploration, we may unlock ultra-fast pathways to new drugs, materials, and technologies — replacing years of lab work with minutes of computation.

⸻

🔹 4. Self-Evolving AI Architectures
Why: Future AI systems will design themselves.
How: Quantum processors will explore massive spaces of model variants in parallel, enabling AI to simulate, compare, and evolve new architectures — fast, efficient, and with little trial-and-error.

⸻

⚛️ The Takeaway:
Quantum computing won’t just speed up AI. It’ll open doors to new types of intelligence — ones that learn, discover, and evolve far beyond today’s limits.

reacted to vincentg64's post with 👀 about 7 hours ago

Post

356

How to Design LLMs that Don’t Need Prompt Engineering https://mltblog.com/3GAbAQu

Standard LLMs rely on prompt engineering to fix problems (hallucinations, poor response, missing information) that come from issues in the backend architecture. If the backend (corpus processing) is properly built from the ground up, it is possible to offer a full, comprehensive answer to a meaningful prompt, without the need for multiple prompts, rewording your query, having to go through a chat session, or prompt engineering. In this article, I explain how to do it, focusing on enterprise corpuses. The strategy relies on four principles:

➡️ Exact and augmented retrieval
➡️ Showing full context in the response
➡️ Enhanced UI with option menu
➡️ Structured response as opposed to long text

I now explain these principles.

Read full article at https://mltblog.com/3GAbAQu

#xLLM #BondingAI #PromptEngineering

reacted to onekq's post with 👍 about 21 hours ago

Post

668

I didn't noticed that Gemini 2.5 (pro and flash) has been silently launched for API preview. Their performance is solid, but below QwQ 32B and the latest DeepSeek v3.

onekq-ai/WebApp1K-models-leaderboard

2 replies

·

reacted to nyuuzyou's post with 👍 about 21 hours ago

Post

872

🖼️ OpenClipart SVG Dataset - nyuuzyou/openclipart

Collection of 178,604 Public Domain Scalable Vector Graphics (SVG) clipart images featuring:
- Comprehensive metadata: title, description, artist name, tags, original page URL, and more.
- Contains complete SVG XML content (minified) for direct use or processing.
- All images explicitly released into the public domain under the CC0 license.
- Organized in a single train split with 178,604 entries.

reacted to mrfakename's post with 🤗👍 about 21 hours ago

Post

723

Hi everyone,

I just launched TTS Arena V2 - a platform for benchmarking TTS models by blind A/B testing. The goal is to make it easy to compare quality between open-source and commercial models, including conversational ones.

What's new in V2:

- **Conversational Arena**: Evaluate models like CSM-1B, Dia 1.6B, and PlayDialog in multi-turn settings
- **Personal Leaderboard**: Optional login to see which models you tend to prefer
- **Multi-speaker TTS**: Random voices per generation to reduce speaker bias
- **Performance Upgrade**: Rebuilt from Gradio → Flask. Much faster with fewer failed generations.
- **Keyboard Shortcuts**: Vote entirely via keyboard

Also added models like MegaTTS 3, Cartesia Sonic, and ElevenLabs' full lineup.

I'd love any feedback, feature suggestions, or ideas for models to include.

TTS-AGI/TTS-Arena-V2

1 reply

·

reacted to merve's post with 🚀 about 21 hours ago

Post

694

you can easily fine-tune, quantize, play with sota vision LM InternVL3 now 🔥
we have recently merged InternVL3 to Hugging Face transformers and released converted checkpoints 🤗

collection for converted checkpoints: merve/internvl3-hf-6814be2943b2ae0e711c92a5
notebook: https://colab.research.google.com/drive/1wAQ7cyjyaCwLXbMA_OjXZe7aCxCFm6sI?usp=sharing 📖

reacted to RiverZ's post with 🤗 about 21 hours ago

Post

671

🚀 Excited to Share Our Latest Work: In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer～

🎨 Daily Paper:
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (2504.20690)

🔓 Code is now open source!
🔥 Huggingface DEMO:
RiverZ/ICEdit

🌐 Project Website: https://river-zhang.github.io/ICEdit-gh-pages/
🏠 GitHub Repository: https://github.com/River-Zhang/ICEdit/blob/main/scripts/gradio_demo.py
🤗 Huggingface:
sanaka87/ICEdit-MoE-LoRA

📄 arxiv Paper:
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer (2504.20690)

🔥 Why it’s cool:
- Achieves high-quality, multi-task image editing.
- Uses only 1% of the training parameters and 0.1% of the training data compared to existing methods — extremely efficient
- Beats several commercial models on background preservation, ID control, and consistency
- Open-source, low-cost, faster, and stronger — think of it as the “DeepSeek of image editing” 👀

We also implemented a Gradio demo app, available directly in our GitHub repo! And we made a flashy demo video — happy to send it your way!

reacted to fdaudens's post with 🔥 about 21 hours ago

Post

931

Forget everything you know about transcription models - NVIDIA's parakeet-tdt-0.6b-v2 changed the game for me!

Just tested it with Steve Jobs' Stanford speech and was speechless (pun intended). The video isn’t sped up.

3 things that floored me:
- Transcription took just 10 seconds for a 15-min file
- Got a CSV with perfect timestamps, punctuation & capitalization
- Stunning accuracy (correctly captured "Reed College" and other specifics)

NVIDIA also released a demo where you can click any transcribed segment to play it instantly.

The improvement is significant: number 1 on the ASR Leaderboard, 6% error rate (best in class) with complete commercial freedom (cc-by-4.0 license).

Time to update those Whisper pipelines! H/t @Steveeeeeeen for the finding!

Model: nvidia/parakeet-tdt-0.6b-v2
Demo: nvidia/parakeet-tdt-0.6b-v2
ASR Leaderboard: hf-audio/open_asr_leaderboard

reacted to daavoo's post with 🚀 about 21 hours ago

Post

652

We've just released a new version of https://github.com/mozilla-ai/any-agent , including a Python implementation of https://huggingface.co/blog/tiny-agents!

Give it a ⭐!

from any_agent import AnyAgent, AgentConfig
from any_agent.config import MCPStdioParams

agent = AnyAgent.create(
    "tinyagent",
    AgentConfig(
        model_id="gpt-4.1-nano",
        instructions="You must use the available tools to find an answer",
        tools=[
            MCPStdioParams(
                command="uvx",
                args=["duckduckgo-mcp-server"]
            )
        ]
    )
)

result = agent.run(
    "Which Agent Framework is the best??"
)
print(result.final_output)

reacted to samihalawa's post with 👀 about 21 hours ago

Post

375

CURSOR IS OVER 📢 Big announcement, folks! 🔥 I'm making a clean break from Cursor, Copilot, Cline, and all those other AI-focused IDEs. 👋

If you're already shelling out for Cursor, Copilot, or similar, honestly, you'd be much better off putting those bucks towards Claude MAX and just taking off!
💰➡️ Claude MAX
WHY?🤔 Claude Coder is now practically UNLIMITED if you're a Claude MAX subscriber. Seriously, it's a game-changer. And of course supports MCP out of the box (they invented it!)
🚀And the absolute best bit? You've got a 99% (make that 100% in my experience, LOL) chance that the code it spits out will be PERFECT: zero bugs. ✨ No more head-scratching debugging sessions! 🥳
It just works so much better, has this massive memory (token limit), and is so autonomous – you can literally let it grind away on a project for hours. ⏳

1 reply

·

reacted to as-cle-bert's post with ❤️ about 21 hours ago

Post

1099

One of the biggest challenges I've been facing since I started developing [𝐏𝐝𝐟𝐈𝐭𝐃𝐨𝐰𝐧](https://github.com/AstraBert/PdfItDown) was handling correctly the conversion of files like Excel sheets and CSVs: table conversion was bad and messy, almost unusable for downstream tasks🫣

That's why today I'm excited to introduce 𝐫𝐞𝐚𝐝𝐞𝐫𝐬, the new feature of PdfItDown v1.4.0!🎉

With 𝘳𝘦𝘢𝘥𝘦𝘳𝘴, you can choose among three (for now👀) flavors of text extraction and conversion to PDF:

- 𝗗𝗼𝗰𝗹𝗶𝗻𝗴, which does a fantastic work with presentations, spreadsheets and word documents🦆

- 𝗟𝗹𝗮𝗺𝗮𝗣𝗮𝗿𝘀𝗲 by LlamaIndex, suitable for more complex and articulated documents, with mixture of texts, images and tables🦙

- 𝗠𝗮𝗿𝗸𝗜𝘁𝗗𝗼𝘄𝗻 by Microsoft, not the best at handling highly structured documents, by extremly flexible in terms of input file format (it can even convert XML, JSON and ZIP files!)✒️

You can use this new feature in your python scripts (check the attached code snippet!😉) and in the command line interface as well!🐍

Have fun and don't forget to star the repo on GitHub ➡️ https://github.com/AstraBert/PdfItDown

reacted to clem's post with 🤗🔥 about 21 hours ago

Post

649

LeRobot-worldwide-hackathon is already scheduled in 30 cities all over the world!

Check if there's one in your city here: LeRobot-worldwide-hackathon/worldwide-map

reacted to DevinGrey's post with 👀 about 21 hours ago

Post

675

hello All. I am new to all of this and just beginning to learn how to use hugging face and AI in general. How can I access an ai code developer for help in setting up a website?

2 replies

·

replied to DevinGrey's post about 21 hours ago

If you are looking for people or resources for a serious project, it may be a good idea to consult Expert Support or check out the collaboration channel on HF Discord.
https://huggingface.co/support
https://discuss.huggingface.co/t/join-the-hugging-face-discord/11263

reacted to sometimesanotion's post with 👀 1 day ago

Post

1163

The capabilities of the new Qwen 3 models are fascinating, and I am watching that space!

My experience, however, is that context management is vastly more important with them. If you use a client with a typical session log with rolling compression, a Qwen 3 model will start to generate the same messages over and over. I don't think that detracts from them. They're optimized for a more advanced MCP environment. I honestly think the 8B is optimal for home use, given proper RAG/CAG.

In typical session chats, Lamarck and Chocolatine are still my daily drives. I worked hard to give Lamarck v0.7 a sprinkling of CoT from both DRT and Deepseek R1. While those models got surpassed on the leaderboards, in practice, I still really enjoy their output.

My projects are focusing on application and context management, because that's where the payoff in improved quality is right now. But should there be a mix of finetunes to make just the right mix of - my recipes are standing by.

reacted to ProCreations's post with 👀 1 day ago

Post

1027

Quantum Computing + AI = 🤯?
What do you think quantum computing will do to AI?
Will it revolutionize training speed? Unlock whole new algorithms? Or maybe… just complicate things?

💬 Drop your thoughts below — we’ll share our take and highlight some of your replies in tomorrow’s post!

1 reply

·

reacted to ginipick's post with 🔥 1 day ago

Post

2303

🎨 Renoir Studio: Impressionist Masterpieces Reborn Through AI ✨

🌟 Experience Renoir's Magical Brushstrokes with AI!

🔗 Try it now: ginigen/flux-lora-renoir
🔗 Model page: openfree/pierre-auguste-renoir
🔗 Collection: openfree/painting-art-ai-681453484ec15ef5978bbeb1

Hello, AI art enthusiasts! 💖
Today I'm introducing a special model - Pierre-Auguste Renoir Studio. Create your own beautiful artwork in the style of the 19th century French Impressionist master! 🖼️
✨ Why Renoir's Style?
Renoir is famous for his luminous colors and soft brushstrokes. His works feature:

🌞 Warm sunshine and dancing light
👨‍👩‍👧‍👦 The beauty of everyday life and joyful moments
🌸 Vibrant nature and portraits of beautiful women
🎭 Lively Parisian social gatherings and outdoor scenes

🔬 Technical Features
This model was developed as a flux-based learning model trained on a curated collection of high-resolution masterpieces from renowned global artists. The LoRA fine-tuning process leveraged exceptional quality open-access imagery released by prestigious institutions including the Art Institute of Chicago. The resulting model demonstrates remarkable capability in capturing the nuanced artistic techniques and stylistic elements across diverse historical art movements! 🧠💫
🚀 How to Use

Describe your desired scene in the prompt box
Add the "renoir" keyword at the end (this is the trigger keyword!)
Click the 'Generate' button
Enjoy your ideas reborn in Renoir's style!

💡 Recommended Prompt Examples

"Elegant ladies enjoying a picnic in a sunlit garden, wearing pastel dresses and hats renoir"
"People boating by a riverbank, light reflecting on water, warmth of summer renoir"
"Paris cafe terrace, people chatting over coffee, evening sunset renoir"

🌈 Now It's Your Turn!
#AI#Renoir #ArtificialIntelligence#HuggingFace #FLUX #LoRA

John Smith PRO

AI & ML interests

Recent Activity

Organizations

John6666's activity