John6666 (John Smith)

reacted to nomadicsynth's post with 👍 about 8 hours ago

Post

632

I Did a Thing!

I made an embedding model to find answers in research papers. It goes deeper than plain "semantic search" by identifying deeply reasoned connections and interdisciplinary insights that might have been overlooked. The goal is to find the solutions that might have been missed and to uncover answers that are already out there.

I’ve set up a demo Space - nomadicsynth/inkling . It’s early days, and I’d love some feedback on the model’s results. Try it out and let me know what you think!

Oh, and if it finds your Nobel-winning answer, I want a cut! 😉

6 replies

·

reacted to giadap's post with 🤗 about 8 hours ago

Post

1397

Ever notice how some AI assistants feel like tools while others feel like companions? Turns out, it's not always about fancy tech upgrades, because sometimes it's just clever design.

Our latest blog post at Hugging Face dives into how minimal design choices can completely transform how users experience AI. We've seen our community turn the same base models into everything from swimming coaches to interview prep specialists with surprisingly small tweaks.

The most fascinating part? When we tested identical models with different "personalities" in our Inference Playground, the results were mind-blowing.

Want to experiment yourself? Our Inference Playground lets anyone (yes, even non-coders!) test these differences in real-time. You can:

- Compare multiple models side-by-side
- Customize system prompts
- Adjust parameters like temperature
- Test multi-turn conversations

It's fascinating how a few lines of instruction text can transform the same AI from strictly professional to seemingly caring and personal, without changing a single line of code in the model itself.

Read more here: https://huggingface.co/blog/giadap/ai-personas

reacted to jeffboudier's post with 👀 about 8 hours ago

Post

637

So many orgs on HF would really benefit from security and governance built into Enterprise Hub - I wrote a guide on why and how upgrade: jeffboudier/how-to-upgrade-to-enterprise

For instance, did you know about Resource Groups?

reacted to wolfram's post with 🤗 about 8 hours ago

Post

1282

Finally finished my extensive **Qwen 3 evaluations** across a range of formats and quantisations, focusing on **MMLU-Pro** (Computer Science).

A few take-aways stood out - especially for those interested in local deployment and performance trade-offs:

1️⃣ **Qwen3-235B-A22B** (via Fireworks API) tops the table at **83.66%** with ~55 tok/s.
2️⃣ But the **30B-A3B Unsloth** quant delivered **82.20%** while running locally at ~45 tok/s and with zero API spend.
3️⃣ The same Unsloth build is ~5x faster than Qwen's **Qwen3-32B**, which scores **82.20%** as well yet crawls at <10 tok/s.
4️⃣ On Apple silicon, the **30B MLX** port hits **79.51%** while sustaining ~64 tok/s - arguably today's best speed/quality trade-off for Mac setups.
5️⃣ The **0.6B** micro-model races above 180 tok/s but tops out at **37.56%** - that's why it's not even on the graph (50 % performance cut-off).

All local runs were done with LM Studio on an M4 MacBook Pro, using Qwen's official recommended settings.

**Conclusion:** Quantised 30B models now get you ~98 % of frontier-class accuracy - at a fraction of the latency, cost, and energy. For most local RAG or agent workloads, they're not just good enough - they're the new default.

Well done, Qwen - you really whipped the llama's ass! And to OpenAI: for your upcoming open model, please make it MoE, with toggleable reasoning, and release it in many sizes. *This* is the future!

2 replies

·

reacted to prithivMLmods's post with 👍 1 day ago

Post

1823

Well, here’s the updated version with the 20,000+ entry sampled dataset for Watermark Filter Content Moderation models incl. [Food25, Weather, Watermark, Marathi/Hindi Sign Language Detection], post-trained from the base models: sigLip2 patch16 224 — now with mixed aspect ratios for better performance and reduced misclassification. 🔥

Models :
➮ Watermark-Detection : prithivMLmods/Watermark-Detection-SigLIP2
⌨︎ Watermark Detection & Batch Image Processing Experimentals, Colab Notebook : https://colab.research.google.com/drive/1mlQrSsSjkGimUt0VyRi3SoWMv8OMyvw3?usp=drive_link
➮ Weather-Image-Classification : prithivMLmods/Weather-Image-Classification
➮ TurkishFoods-25 : prithivMLmods/TurkishFoods-25
➮ Marathi-Sign-Language-Detection : prithivMLmods/Marathi-Sign-Language-Detection
➮ Hindi-Sign-Language-Detection : prithivMLmods/Hindi-Sign-Language-Detection

Datasets :
Watermark : qwertyforce/scenery_watermarks
Weather : prithivMLmods/WeatherNet-05-18039
Turkish Foods 25 : yunusserhat/TurkishFoods-25
Marathi Sign Language : VinayHajare/Marathi-Sign-Language
Hindi Sign Language : Vedant3907/Hindi-Sign-Language-Dataset

Collection : prithivMLmods/content-filters-siglip2-vit-68197e3357d4de18fb3b4d2b

reacted to sequelbox's post with 👀 1 day ago

Post

1516

NEW RELEASE: Esper 3 for Qwen 3!

- A full-stack software assistant: a reasoning finetune focused on coding, architecture, and DevOps using the Titanium and Tachibana datasets!
- Improved general and creative reasoning skills, powered by the Raiden dataset.

4B model: ValiantLabs/Qwen3-4B-Esper3
8B model: ValiantLabs/Qwen3-8B-Esper3

We'll also be bringing Esper 3 to larger Qwen 3 models as soon as we can - if you want these, consider helping us out: sequelbox/SupportOpenSource

More models and datasets to come soon!

with my love and enthusiasm,
allegra

reacted to Dutra0530's post with 👀 1 day ago

Post

2068

Guys, every time I try to change something, or save my project, this strange error appears. Does anyone know how to solve it?

5 replies

·

replied to Dutra0530's post 1 day ago

I've seen this bug before, but I can't figure out what's causing it...😅
https://discuss.huggingface.co/t/getting-unexpected-token-doctype-is-not-valid-json-in-datasets-viewer/146444

reacted to davidberenstein1957's post with 👍 1 day ago

Post

710

Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs

https://huggingface.co/blog/davidberenstein1957/phare-analysis-of-hallucination-in-leading-llms

reacted to clem's post with ❤️ 1 day ago

Post

3284

What are you using to evaluate models or AI systems? So far we're building lighteval & leaderboards on the hub but still feels early & a lot more to build. What would be useful to you?

6 replies

·

reacted to AdinaY's post with 😎 1 day ago

Post

3164

ACE-Step 🎵 a music generation foundation model released by
StepFun & ACEStudio

Model: ACE-Step/ACE-Step-v1-3.5B
Demo: ACE-Step/ACE-Step

✨ 3.5B, Apache2.0 licensed
✨ 115× faster than LLMs (4-min music in 20s on A100)
✨ Diffusion + DCAE + linear transformer = speed + coherence
✨ Supports voice cloning, remixing, lyric editing & more

1 reply

·

reacted to AdinaY's post with 🚀 1 day ago

Post

592

CCI4.0-M2 📊 A powerful dataset with 3 specialized subsets, released by
BAAIBeijing

BAAI/cci40-68199d90bbc798680df16d7c

✨ M2-Base: 3.5TB web data (EN/ZH), with LLM-augmented content, APACHE2.0
✨ M2-CoT: 4.2TB of auto-synthesized CoT reasoning data
✨ M2-Extra: domain-specific knowledge

reacted to merve's post with 🔥 1 day ago

Post

3726

A ton of impactful models and datasets in open AI past week, let's summarize the best 🤩 merve/releases-apr-21-and-may-2-6819dcc84da4190620f448a3

💬 Qwen made it rain! They released Qwen3: new dense and MoE models ranging from 0.6B to 235B 🤯 as well as Qwen2.5-Omni, any-to-any model in 3B and 7B!
> Microsoft AI released Phi4 reasoning models (that also come in mini and plus sizes)
> NVIDIA released new CoT reasoning datasets
🖼️ > ByteDance released UI-TARS-1.5, native multimodal UI parsing agentic model
> Meta released EdgeTAM, an on-device object tracking model (SAM2 variant)
🗣️ NVIDIA released parakeet-tdt-0.6b-v2, a smol 600M automatic speech recognition model
> Nari released Dia, a 1.6B text-to-speech model
> Moonshot AI released Kimi Audio, a new audio understanding, generation, conversation model
👩🏻‍💻 JetBrains released Melium models in base and SFT for coding
> Tesslate released UIGEN-T2-7B, a new text-to-frontend-code model 🤩

reacted to sharpenb's post with 🚀 1 day ago

Post

2881

How to learn about efficient AI? - Happy to announce the Awesome AI Efficiency repo that gathers a curated list of 100+ materials to understand the challenges and solutions in making AI faster, smaller, cheaper, greener.

🚀 It is designed for a **large audience** including beginners, decision-makers, engineers, and researchers.
📚 It contains **diverse materials** with newspaper articles, blogs, tools, tech reports, research papers, books, and lectures.

This is an ongoing project. Do not hesitate to share your feedback/suggestions and star the repo! 🌟

https://github.com/PrunaAI/awesome-ai-efficiency

2 replies

·

reacted to RiverZ's post with 🤗 1 day ago

Post

4443

🔥 We're thrilled to share some exciting news about ICEdit! Currently, ICEdit app ( RiverZ/ICEdit) has soared to the second place on the weekly trend list of Hugging Face Space, just trailing behind Qwen3. What's more, it also holds the second position on the overall space trend list. This achievement wouldn't have been possible without your incredible support and love. A huge thank you to each and every one of you❤!

🎉 The ICEdit community has been incredibly active, and we've seen a plethora of amazing ComfyUI workflows being shared. For instance, with the help of ComfyUI - nunchaku, you can run ICEdit locally with just 4GB of VRAM. This makes it much more accessible for those with limited hardware resources.

🎇 If you're interested in the detailed information, please head over to our repository. We highly encourage you to give these workflows a try and explore the creative possibilities that ICEdit offers.

Github Repo: https://github.com/River-Zhang/ICEdit
Hugging Face Space: RiverZ/ICEdit

reacted to VirtualOasis's post with 👍 1 day ago

Post

2466

Agents vs. Workflows
Agents are systems where LLMs dynamically direct their processes and tool usage, maintaining control over how they accomplish tasks.
Workflows are through predefined code paths, ensuring that each step is executed in a deterministic manner.

Agents are like smart assistants that can think on their own. They understand situations, make decisions, and act, whatever the task is new or unpredictable. Think of the Agent as a chef who can make a meal based on what they have.

Workflows are like a recipe with fixed steps. They’re a series of tasks done in order, like following a checklist for approving a loan. They’re great for tasks that don’t change much.

1 reply

·

reacted to ProCreations's post with 🧠 2 days ago

Post

629

🚨 NEW DATASET ALERT 🚨

Come check out
ProCreations/black-hole-sim-randomized
a high-fidelity dataset with 400,000+ randomized black hole simulations — packed with relativistic metrics, Kerr geometry, and GR weirdness to help AIs actually understand physics.

🕳️ Teach your model:
• Time dilation
• Redshift
• Orbital dynamics
• Frame dragging
• Full Kerr tensors
…and more, all in raw JSONL!

This release celebrates SimpleMath hitting 200 downloads — thank you all so much for the support! 🙌

reacted to Jaward's post with 🔥 2 days ago

Post

578

Thrilled to share our latest work: Voila - a family of fully opensourced voice models for real-time autonomous convos and role-play, some of our major contributions include 🧵:
1) An End-to-End Full-Duplex Arch: that directly processes & handles simultaneous audio token streams from user to model and vice versa.
2) Voila-Tokenizer: A 100K-hour trained tokenizer with interleaved alignment (audio & text) that distills semantic/acoustic tokens via RVQ.
3) Text-Audio Interleaved Alignment: We leveraged a fine-grained alignment of text and audio tokens that allows synchronization and expressiveness for tasks like ASR (WER 2.7%) and TTS (WER 2.8%).
4) Voice Customization: Supports 1M+ pre-built voices and 1 shot voice clone from 10s audio clips using Wespeaker embeddings.

Models: maitrix-org/voila-67e0d96962c19f221fc73fa5
Code: https://github.com/maitrix-org/Voila
Demo: maitrix-org/Voila-demo
Project page: maitrix-org/Voila-demo

2 replies

·

reacted to ZennyKenny's post with 🧠 2 days ago

Post

2989

After hearing the news that Marc Andreessen thinks that the only job that is safe from AI replacement is venture capital: https://gizmodo.com/marc-andreessen-says-one-job-is-mostly-safe-from-ai-venture-capitalist-2000596506 🧠🧠🧠

The Reasoned Capital synthetic dataset suddenly feels much more topical: ZennyKenny/synthetic_vc_financial_decisions_reasoning_dataset 🔥🔥🔥

Really looking forward to potentially expanding this architecture and seeing how algorithmic clever investment truly is! 💰💰💰

reacted to merve's post with 🚀 3 days ago

Post

5646

A real-time object detector much faster and accurate than YOLO with Apache 2.0 license just landed to Hugging Face transformers 🔥

D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩

> Collection with all checkpoints and demo ustc-community/d-fine-68109b427cbe6ee36b4e7352

Notebooks:
> Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb
> Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb
> Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb
h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩

Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️

D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩

Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️

this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.

2 replies

·

John Smith PRO

AI & ML interests

Recent Activity

Organizations

John6666's activity