Tag: hugging face

Agents recall past sessions 8x cheaper than handoffs

Written by Felipe Santos on October 21, 2026. Posted in AI.

Coding agents forget everything when a session ends, so each new agent on each new machine starts from zero. Hugging Face's funes is an open-source memory layer that indexes the sessions already on your machine and lets Claude Code, Codex, pi, and Hermes recall past decisions, rationale, and dead ends. In the team's benchmark, recall was 8x cheaper than a written handoff on one task and 4x cheaper on the other. The article builds on an earlier argument that coding agents already produce the record we keep losing: as they search, try approaches, hit errors, and change direction, they leave a...

FLUX.3 Image Klein renders 1024×1024 images in 2 seconds

Written by Felipe Santos on October 21, 2026. Posted in AI.

Black Forest Labs' FLUX.3 Image Klein runs in Hugging Face Diffusers from day one. One model handles text-to-image and multi-reference image-to-image, and it adds a new capability: layout control. You write bounding boxes into the prompt to say where each part of the image should go, or which parts of a reference image to move. The distilled checkpoint makes a 1024 × 1024 image in about 2 seconds on an H100. Both open checkpoints are in the FLUX.3 Image Klein collection on the Hub: black-forest-labs/flux-3-image-klein and black-forest-labs/flux-3-image-klein-base. You can also try the model...

IBM packs speech and decisions into one model

Written by Felipe Santos on October 17, 2026. Posted in AI.

IBM's Granite Switch 4.1 models combine a general-purpose Decision adapter, a specialized Guardian adapter, and the fastest ASR model on the OpenASR leaderboard into one model. They can move between natural-language responses, decision tasks, and speech-to-text, all from one hosted endpoint. The models are Granite-Switch-4.1-8B and Granite-Switch-4.1-30B. The Decision adapter is new and handles general-purpose decision-making, such as the v1/systemone decisions the article cites. The Guardian aLoRA is specialized for safety-related decision tasks. The article says it outperforms Jev 1.13,...

Multimodal Open d1 Decision Models for the Edge

Written by Felipe Santos on October 9, 2026. Posted in AI.

Liquid AI has released two open-weight decision models: d1-3B and d1-omni-600M (experimental). Unlike generative models that produce tokens sequentially, decision models answer questions in a single forward pass, making them suitable for edge deployment. d1-3B is trained from LFM2.5-VL-3B, a decoder-only vision language model that accepts text and images. d1-omni-600M is trained from LFM2.5-Encoder-350M, a bidirectional encoder that adds vision and audio encoders, accepting either text and images or text and audio as inputs. The d1-omni-600M model is currently in early research release and...

ML-Intern: Six AI Models Built From a Single Prompt

Written by Felipe Santos on October 9, 2026. Posted in AI.

Last week, I wanted a small version of the prompt rewriter that ships with Qwen-Image 2.1. The official one is a 9B model that needs about 20 GB of memory and thinks for thousands of tokens before writing a single paragraph. The Hub had only compressed copies of that same 9B model. So I described what I wanted to ML-Intern, and the next day I had a 0.8B version that runs on a CPU. It returns valid output 99.7% of the time and uses about a quarter of the teacher's tokens. The compute for the whole project, including having the 9B model label 8,797 example requests, came to USD 16. Over the...

A falcon draped in the UAE flag stands against a purple Dubai skyline, with text announcing Falcon-H1-Emirati, a new Emirati Arabic language model.

Falcon-Emirati-7B: A Dialect-Specialized Model for Emirati Arabic

Written by Felipe Santos on October 7, 2026. Posted in AI.

Arabic is really a family of languages living under one name. Modern Standard Arabic is what you read in the news or a textbook, but it's rarely how people actually talk to each other. In the UAE, day-to-day conversation, humor, negotiation, and storytelling happen in Emirati Arabic, a Gulf dialect with its own vocabulary, its own rhythm, and a culture wrapped tightly around it. Emirati poetry, especially nabati poetry, along with proverbs and short anecdotes, carries meaning that doesn't survive a literal, word-for-word reading. A model that only knows MSA can translate every word of an...

Allen AI Releases AstaBrief 8B, an Open-Weights Model for Scientific Report Generation

Written by Felipe Santos on October 3, 2026. Posted in AI.

Language models can help researchers search literature, synthesize evidence, and work through complex questions. But scientific work places particular demands: answers must stay grounded in evidence, models must preserve what evidence actually supports rather than broadening conclusions, and researchers need to verify outputs. Allen AI observed this in how scientists use Asta, its agentic platform for scientific work. Instead of simple keyword searches, users bring substantial context and constraints—for example, asking Asta to compare approaches across literature while accounting for...

NVIDIA Releases Kumo Tabular, an Open Foundation Model for Tabular Data

Written by Felipe Santos on September 30, 2026. Posted in AI.

NVIDIA has released Kumo Tabular, an open foundation model for tabular classification and regression available on Hugging Face. The model predicts labels for new rows in a single forward pass without training, tuning, or feature engineering. It comes in three sizes ranging from 28M to 215M parameters, runs through NVIDIA's open-source library, and is released under the OpenMDW-1.1 license for commercial use. Model Size Parameters Small 28M Medium ~122M Large 215M Kumo Tabular ranks first on four major benchmarks: TabArena, BeyondArena, TALENT, and ScoringBench. The Problem...

A black square with a white bird outline, an orange X, and a yellow clapping hands emoji on a gradient background.

Jun Kim Joins Hugging Face to Lead MLX Framework

Written by Felipe Santos on September 26, 2026. Posted in AI.

MLX is Apple's framework for local AI, optimized for Apple Silicon. Hugging Face has supported MLX since its launch as a Christmas present from Awni Hannun and Angelos Katharopoulos in 2023, and the Hub now serves as the primary repository where people find and contribute MLX models. The project is graduating from a side effort to a fully maintained and funded initiative The project is graduating from a side effort to a fully maintained and funded initiative, which will provide stability and faster development. Jun will lead the effort full-time, better guiding contributors and planning for...

Tag: hugging face

Privacy Settings

Functional

Preferences