🍓 One of the coolest parts about being an early Strawberry user has been the opportunity to build on the app at the ground floor.
The platform already has a ton of great integrations that let you interact with your external apps directly with tools, but I wanted to add the ability to do stuff in Slack as well.
💪 So I took the base Anthropic Slack MCP server, added a whole bunch of new tools, and generalized it as an HTTP-based SSE-server and deployed it in like 2 minutes with Railway so that Strawberry could make use of it (as can Claude or any other MCP client).
Now, you can Chat with your Strawberry Companion (or Claude, or whatever) and do things like: ➡️ Get caught up across all of your Slack channels after a long weekend or noisy incident without having to read 20 threads in 10 different channels ➡️ Create, read, and edit Canvases, Messages, and Channels ➡️ Take any resources or content that you're using in your Chat and inject it directly into Slack without copy / paste
😎 I'm pretty pleased with the results, and I made a short demo video showing the results of the work (link in comments). The best part is, it's available on GitHub for anyone else to use too (link in the comments, instructions in the README). The setup takes about 5-10 minutes.
Demo for Molmo2 on Hugging Face is live now, including Single/Multi-Image VQA, Visual Pointing/Grounding, Video VQA, and Video Point Tracking. Find the demo and related collections below. 🔥🤗
Introducing the Z Image Turbo LoRA DLC App, a gallery space for plug-and-play Z-Image-Turbo LoRAs. It features a curated collection of impressive LoRAs for generating high-quality images. By default, it runs on the base model. Simply choose a LoRA, type your prompt, and generate images. You can find the app and more details below. 🤗🧪
Introducing the D.Markdown Experimental Models, Proxima and Epsilon OCR models, built on top of Qwen3-VL and Qwen2.5-VL respectively. Proxima is optimized for Markdown generation and is capable of embedding inline programming code snippets and generating rich nodes such as HTML, XML, JSON, and YAML. Epsilon is optimized for reconstructing complex layouts including tables, forms, and mathematical content. 🌌✨
We have covered Tensor Parallelism for slicing matrices and Pipeline Parallelism for stacking layers. But what if your model isn't just deep or wide—it's a sprawling Mixture-of-Experts (MoE) architecture like Mixtral or DeepSeek, with trillions of parameters that are mostly idle per token?
Replicating those experts wastes VRAM. Slicing them with TP wastes bandwidth. The solution is Expert Parallelism (EP), which distributes the experts themselves across GPUs and routes tokens to wherever their "chosen" expert lives.
The hardware catch? It is not matrix splitting or pipeline bubbles—it's the "Router's Dilemma." You must shuffle massive volumes of tokens across the cluster using All-to-All communication, and any imbalance can leave expensive GPUs idle.
My latest guide dives into the mechanics of EP and why the interconnect becomes the ultimate bottleneck.
In this breakdown, we explore:
The Token Routing Lifecycle A four-step hardware flow: Local routing to pick experts, Dispatch (All-to-All shuffle), Expert computation on the "home" GPU, and Combine (another All-to-All to return results).
The All-to-All Primitive Unlike the ring-based syncs in TP, All-to-All creates a dense mesh of personalized data transfers. We compare it to All-Reduce and show why uneven token distribution (load imbalance) causes network congestion and compute skew.
Load Balancing: The Hardware Nightmare If one expert gets 90% of the tokens, its GPU bottlenecks while others stall. We discuss mitigation strategies like token dropping and auxiliary losses to keep utilization high.
The article includes a raw PyTorch implementation of an EP layer using torch.distributed.all_to_all_single to reveal exactly how the data shuffles and where the stalls happen.
Try CUA GUI Operator 🖥️ Space, the demo of some interesting multimodal ultra-compact Computer Use Agent (CUA) models in a single app, including Fara-7B, UI-TARS-1.5-7B, and Holo models, to perform GUI localization tasks.
I have planned to add Chrome sandboxes to streamline it and turn it into a browser based CUA multimodal tool, which will be added to the same space soon.
To know more about it, visit the app page or the respective model page!
What a trip. Just walked through @burtenshaw and @evalstate tutorial on adding Hugging Face Skills to your Claude Code agent so you can fine tune LLMs by chatting with AI.
These are the kinds of innovations that are going to help everyone benefit from the power of Artificial Intelligence. Well done gentlemen and thank you for sharing.
One speech model with seven voices, streamlined with multimodal capabilities for vision tasks. Performs vision(image-text) to audio inference with Qwen2.5-VL + VibeVoice-Realtime-0.5B. Vision to VibeVoice (EN) - The demo is live. 🗣️🔥
strangerzonehf [HF] Community / Organization Page, which is maintained by me, has reached the Top 10 Developer Pages ranking at 6th place, contributing 3.4% in the calendar cycle from August 2024 to August 2025. It is also the only South Asia / Indian page in the list. I could not be more proud to be doing things for the community. ❤️🤗
We recently discussed how Tensor Parallelism slices matrices to reduce latency within a single node. But what happens when you need to scale beyond that, where the bandwidth drops?
That is where Pipeline Parallelism (PP) takes over.
Instead of slicing the operation, PP slices the model depth. It turns your GPU cluster into an assembly line: GPU 0 handles layers 1-12, GPU 1 handles 13-24, and so on.
The hardware challenge here isn't the interconnect speed—it is the "Pipeline Bubble." In a naive setup, expensive H100s sit idle for most of the cycle waiting for data to flow through the chain.
My latest guide breaks down the scheduling strategies used to minimize this idle silicon time.
In this deep dive, we cover:
The Hardware Mechanics: Vertical Slicing Unlike TP which requires "chatty" All-Reduce operations, PP relies on lightweight Point-to-Point (Send/Recv) communication. This makes it the only viable strategy for crossing node boundaries over Ethernet or InfiniBand.
Fighting the Bubble: 1F1B vs. GPipe We analyze the scheduling algorithms that keep the GPUs fed:
GPipe: The "flush and fill" approach. Simple, but memory-intensive. 1F1B (One-Forward-One-Backward): The industry standard. By interleaving forward and backward passes, we aggressively free up memory and reduce the bubble size. The Math of Efficiency The "Bubble" is a mathematical inevitability. We look at the efficiency formula M+N−1 M to understand why you need massive global batch sizes to make PP worth the effort.
The article includes a conceptual PyTorch implementation of the 1F1B state machine to illustrate exactly how the data is handed off between stages.
😐 I keep seeing takes on LinkedIn from American business influencers melting down about Silicon Valley startup "dependence" on open-source Chinese models.
🤔 Can anyone describe a credible scenario where these models can be leveraged by the Chinese government to endanger American security interests or am I right to believe that this is just Red Scare nonsense?
Introducing the Super-OCRs Demo, a comparison of state-of-the-art multimodal OCR VLMs, including HunyuanOCR, DeepSeekOCR, Dots, and Nanonets in one space for performing OCR, rendering LaTeX and Markdown, and visual grounding (layout). Find the related Spaces and models below.🤗🔥
When models get too large for a single GPU, simply stacking layers vertically (Pipeline Parallelism) isn't always the answer. Sometimes, you need to slice the matrices themselves.
My latest guide breaks down the hardware mechanics of Tensor Parallelism (TP). We look at how to shard individual operations across devices to make a cluster function as one massive accelerator.
This isn't high-level theory—it is a look at the bare metal implementation.
Here is what is covered in the deep dive:
The Strategies: Column vs. Row Parallelism We analyze how to split weight matrices (W) and inputs (X).
Column-Linear: Splits weights by columns. Requires an All-Gather to reconstruct the output. Row-Linear: Splits weights by rows. Requires an All-Reduce to sum partial results. The "Megatron-LM" Optimization Efficiency comes from minimizing communication. By sandwiching the non-linearity (GeLU) between a Column-Parallel layer and a Row-Parallel layer, we can skip synchronization entirely during the activation phase. This cuts communication events by 50% per block.
The Hardware Reality: The Bandwidth Wall In TP, the dist.all_reduce operation sits on the critical path. The CUDA cores effectively stall while waiting for the ring-reduce to finish.
Intra-Node: Works well because NVLink provides enough bandwidth to hide this latency. Inter-Node: Fails at scale. Standard networking (Ethernet/InfiniBand) is too slow for the high-frequency syncs required by TP. The article includes a raw PyTorch implementation using torch.distributed primitives to show exactly where the data moves and where the bottlenecks sit.
Introducing the advanced sketch-board editor "Nano-Banana-Pro-Sketch-Board" powered by the Gemini 2.5 Flash Image and Gemini 3 Pro Preview Image models through the Gemini API. This version includes more features than the Nano-Banana-AIO app for drawing and prompt-based concept transformation of freestyle sketches. 🔥🍌
Note: The Nano-Banana-Pro-Sketch-Board demo requires a Gemini API key for the editing process. Your API key will be removed when the app is reloaded or closed. Your key remains safe and will not be exposed to any medium. Also, the Gemini 3 Pro Preview Image model may require a paid API key from a Google Cloud project with billing enabled.
To know more about it, visit the app info section or the respective Model Garden page!
Try the demo of NVIDIA Nemotron Parse v1.1, NVIDIA's latest VLM for understanding document semantics and extracting text and table elements with spatial grounding. It is capable of comprehensive text understanding and document structure analysis in a given document, and can provide bounding boxes with coordinates.
Try the all-new trending Qwen-Image-Edit-2509 (Multi-Image-Edits) specialized adapter demos, including Cloth-Design-Fuse, Texture Edit, Guided-Objects-Patching, and more — all in a single Hugging Face Space. The demo link is provided below. 🤗🔥
Made a demo for multimodal understanding of Qwen3-VL space for tasks including point annotation, detection, captioning, guided text inferences, and more. Find the demo link below. 🤗↗️
