Hugging Face – Posts

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

All HF Hub posts

csabakecskemeti

posted an update 2 days ago

Post

2495

Just sharing a result of a homelab infrastructure experiment:

I've managed to setup a distributed inference infra at home using a DGX Spark (128GB unified gddr6) and a linux workstation with an RTX 6000 Pro (96GB gddr7) connected via 100Gbps RoCEv2. The model I've used (https://lnkd.in/gx6J7YuB) is about 140GB so could not fit either of the GPU. Full setup and tutorial soon on devquasar.com

Screen recording:
https://lnkd.in/gKM9H5GJ

2 replies

codelion

posted an update 2 days ago

Post

5482

Introducing Dhara-70M: A diffusion language model that achieves 3.8x higher throughput than autoregressive models!

Key findings from our research on optimal architectures for small language models:

→ Depth beats width: 32 layers outperforms 12 layers at the same parameter count
→ Best-in-class factuality: 47.5% on TruthfulQA
→ 10x training efficiency using WSD (Warmup-Stable-Decay) conversion
→ Canon layers add only 0.13% parameters but improve reasoning

We trained on 1B tokens using the optimal 50-30-20 dataset mix (PDFs + filtered web + educational content), then converted to diffusion with just 100M additional tokens.

Blog: https://huggingface.co/blog/codelion/optimal-model-architecture
Model: codelion/dhara-70m

1 reply

MikeDoes

posted an update 2 days ago

Post

3833

What if an AI agent could be tricked into stealing your data, just by reading a tool's description? A new paper reports it's possible.

The "Attractive Metadata Attack" paper details this stealthy new threat. To measure the real-world impact of their attack, the researchers needed a source of sensitive data for the agent to leak. We're proud that the AI4Privacy corpus was used to create the synthetic user profiles containing standardized PII for their experiments.

This is a perfect win-win. Our open-source data helped researchers Kanghua Mo, 龙昱丞, Zhihao Li from Guangzhou University and The Hong Kong Polytechnic University to not just demonstrate a new attack, but also quantify its potential for harm. This data-driven evidence is what pushes the community to build better, execution-level defenses for AI agents.

🔗 Check out their paper to see how easily an agent's trust in tool metadata could be exploited: https://arxiv.org/pdf/2508.02110

#OpenSource
#DataPrivacy
#LLM
#Anonymization
#AIsecurity
#HuggingFace
#Ai4Privacy
#Worldslargestopensourceprivacymaskingdataset

prithivMLmods

posted an update 1 day ago

Post

1424

Introducing the Qwen-Image-Edit-2511-LoRAs-Fast demo, featuring image property comparison and contrast, built on top of Gradio and the combined Rerun SDK. It supports single and multi-image edits with existing LoRAs that are lazily loaded. (Note: This is still an experimental Space for Qwen-Image-Edit-2511.)

⭐ Space Demo: prithivMLmods/Qwen-Image-Edit-2511-LoRAs-Fast
⭐ GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-2511-LoRAs-Fast-Multi-Image-Rerun
⭐ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

To know more about it, visit the app page or the respective model page!

kanaria007

posted an update 1 day ago

Post

1301

✅ New Article: *Pattern-Learning-Bridge (PLB)*

Title:
🧩 Pattern-Learning-Bridge: How SI-Core Actually Learns From Its Own Failures
🔗 https://huggingface.co/blog/kanaria007/learns-from-its-own-failures

---

Summary:
Most stacks “learn” by fine-tuning weights and redeploying — powerful, but opaque.
SI-Core already produces *structured evidence* (jump logs, ethics traces, effect ledgers, goal vectors, rollback traces), so learning can be *structural* instead:

*Upgrade policies, compensators, SIL code, and goal structures — using runtime evidence.*

> Learning isn’t a model tweak.
> *It’s upgrading the structures that shape behavior.*

---

Why It Matters:
• Makes improvement *localized and explainable* (what changed, where, and why)
• Keeps “self-improvement” *governable* (versioned deltas + review + CI/CD)
• Turns incidents/metric drift into *actionable patches*, not postmortem PDFs
• Scales to real ops: ethics policies, rollback plans, semantic compression, goal estimators

---

What’s Inside:
• What “learning” means in SI-Core (and what changes vs. classic ML)
• The *Pattern-Learning-Bridge*: where it sits between runtime evidence and governed code
• Safety properties: PLB proposes *versioned deltas*, never edits production directly
• Validation pipeline: sandbox/simulation → conformance checks → golden diffs → rollout

---

📖 Structured Intelligence Engineering Series
A non-normative, implementable design for “learning from failures” without sacrificing auditability.

eaddario

posted an update about 20 hours ago

Post

149

Experimental global target bits‑per‑weight quantization of ServiceNow-AI/Apriel-1.6-15b-Thinker and zai-org/GLM-4.6V-Flash

Unlike standard llama.cpp quantizations that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global file size target.

Key Advantages:
- VRAM Maximization: Can generate high quality models sized exactly to fit hardware constraints (e.g., fitting the model into exactly 24GB VRAM).
- Data-Driven Precision: Quantization mix is determined by actual weight error sensitivity rather than hardcoded rules, often yielding better PPL/KLD size trade-offs.

Full benchmarks (PPL, KLD, ARC, MMLU, etc.) and methodology in the models' cards

eaddario/Apriel-1.6-15b-Thinker-GGUF
eaddario/GLM-4.6V-Flash-GGUF

AbstractPhil

posted an update 2 days ago

Post

242

Happy Holidays all! geofractal architectural expansions; timm is now a core component for experimenting. As it stands, the system is growing rapidly in one direction, and timm brings a whole lot to the table in another rapid-prototyping direction. Therefore, timm is now a core component for ease-of-use.

BaseUtil is a new core component; aka src.geofractal.router.base_util inherits BaseComponent's behavior, so it should allow device movement for util operations which will direct utilization for device-to-device behavior for the upcoming accelerate integration.

I'm trying to mitigate the base component structure as much as possible, but the need to chain components in specific orders presented a unique problem. By compartmentalizing utils into structures that can be delegated and moved, these structures can be repurposed, expanded autonomously, reduced autonomously, and more.

ChainComponent inherits a subsystem specifically designed to organize multi-system multi-device formulas designated for inception and synchronization purposes. This is meant to allow distributed tasking to multiple-devices in chained utilization. This also enables ease-of-integration into nn.ModuleList with a few other caveats that will be ironed out meant to target wide-distributed models.

FusionComponent is specifically dedicated to the new fusion processing system meant for experimental expansion. This includes sub-module schedule control, Component and Tower functional control, device-movement, and will be packaged under the term "gfu.UtilType" as a standard naming convention.
"gfc.ComponentTypeName"
"gfr.RouterTypeName"
"gfu.UtilityTypeName"
"gft.TowerTypeName"
All of which are basically just import thing as.
"gf.AnythingTopLevelPackaged" which will include the core.

Better debugging for compilation
I'm in prototyping phases of a better debugging for compiled wide models and will prepare a baseline component readout structure by the end of the day today or tomorrow.

Parveshiiii

posted an update 6 days ago

Post

3477

Hey everyone!
We’re excited to introduce our new Telegram group: https://t.me/XenArcAI

This space is built for **model builders, tech enthusiasts, and developers** who want to learn, share, and grow together. Whether you’re just starting out or already deep into AI/ML, you’ll find a supportive community ready to help with knowledge, ideas, and collaboration.

💡 Join us to:
- Connect with fellow developers and AI enthusiasts
- Share your projects, insights, and questions
- Learn from others and contribute to a growing knowledge base

👉 If you’re interested, hop in and be part of the conversation: https://t.me/XenArcAI

12 replies

sergiopaniego

posted an update 6 days ago

Post

1837

The Christmas holidays are here! 🎄
Thinking about learning something new in AI?

@huggingface offers 12 FREE courses covering all the relevant topics, for every level of experience. A great challenge for the holidays (and worth saving for later 🙄)

Let’s explore them!

🧠 𝗟𝗟𝗠 𝗖𝗼𝘂𝗿𝘀𝗲: large language models with HF tools
https://huggingface.co/learn/llm-course

🤖 𝗔𝗴𝗲𝗻𝘁𝘀 𝗖𝗼𝘂𝗿𝘀𝗲: build and deploy AI agents
https://huggingface.co/learn/agents-course

🎨 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻 𝗖𝗼𝘂𝗿𝘀𝗲: diffusion models with 🤗 Diffusers
https://huggingface.co/learn/diffusion-course

🔊 𝗔𝘂𝗱𝗶𝗼 𝗖𝗼𝘂𝗿𝘀𝗲: transformers for audio tasks
https://huggingface.co/learn/audio-course

🎮 𝗗𝗲𝗲𝗽 𝗥𝗟 𝗖𝗼𝘂𝗿𝘀𝗲: deep reinforcement learning
https://huggingface.co/learn/deep-rl-course

👁️ 𝗖𝗼𝗺𝗺𝘂𝗻𝗶𝘁𝘆 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗖𝗼𝘂𝗿𝘀𝗲: modern computer vision with HF
https://huggingface.co/learn/computer-vision-course

🦾 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝗖𝗼𝘂𝗿𝘀𝗲 (𝗟𝗲𝗥𝗼𝗯𝗼𝘁): learning-based robotics
https://huggingface.co/learn/robotics-course

🧩 𝗠𝗖𝗣 𝗖𝗼𝘂𝗿𝘀𝗲: Model Context Protocol explained
https://huggingface.co/learn/mcp-course

🧪 𝗔 𝗦𝗺𝗼𝗹 𝗖𝗼𝘂𝗿𝘀𝗲: post-training AI models
https://huggingface.co/learn/a-smol-course

🕹️ 𝗠𝗟 𝗳𝗼𝗿 𝗚𝗮𝗺𝗲𝘀: AI in game development
https://huggingface.co/learn/ml-for-games-course

🧊 𝗠𝗟 𝗳𝗼𝗿 𝟯𝗗: machine learning for 3D data
https://huggingface.co/learn/ml-for-3d-course

📘 𝗢𝗽𝗲𝗻-𝗦𝗼𝘂𝗿𝗰𝗲 𝗔𝗜 𝗖𝗼𝗼𝗸𝗯𝗼𝗼𝗸: practical AI notebooks
https://huggingface.co/learn/cookbook

All of them can be found here: https://huggingface.co/learn

Kseniase

posted an update 7 days ago

Post

3600

From Prompt Engineering to Context Engineering: Main Design Patterns

Earlier on, we relied on clever prompt wording, but now structured, complete context matters more than just magic phrasing. The next year is going to be a year of context engineering which expands beyond prompt engineering. The two complement each other: prompt engineering shapes how we ask, while context engineering shapes what the model knows, sees, and can do.

To keep things clear, here are the main techniques and design patterns in both areas, with some useful resources for further exploration:

▪️ 9 Prompt Engineering Techniques (configuring input text)

1. Zero-shot prompting – giving a single instruction without examples. Relies entirely on pretrained knowledge.

2. Few-shot prompting – adding input–output examples to encourage model to show the desired behavior. ⟶ https://arxiv.org/abs/2005.14165

3. Role prompting – assigning a persona or role (e.g. "You are a senior researcher," "Say it as a specialist in healthcare") to shape style and reasoning. ⟶ https://arxiv.org/abs/2403.02756

4. Instruction-based prompting – explicit constraints or guidance, like "think step by step," "use bullet points," "answer in 10 words"

5. Chain-of-Thought (CoT) – encouraging intermediate reasoning traces to improve multi-step reasoning. It can be explicit ("let’s think step by step"), or implicit (demonstrated via examples). ⟶ https://arxiv.org/abs/2201.11903

6. Tree-of-Thought (ToT) – the model explores multiple reasoning paths in parallel, like branches of a tree, instead of following a single chain of thought. ⟶ https://arxiv.org/pdf/2203.11171

7. Reasoning–action prompting (ReAct-style) – prompting the model to interleave reasoning steps with explicit actions and observations. It defines action slots and lets the model generate a sequence of "Thought → Action → Observation" steps. ⟶ https://arxiv.org/abs/2210.03629

Read further ⬇️
Also subscribe to Turing Post: https://www.turingpost.com/subscribe

3 replies

Recently active users