The top 5 hugging face models & datasets measured by RiseFinder over the 1d window ending 7 October 2026.
Taiga-S1 is a small, fast decision model designed for computer-use agents, where a planner decides what to do and a tiny model handles step-by-step execution. It is an experiment testing whether such models can be useful in this role, with FreeCAD serving as the testbed. The stated next step is applying the same approach to applications without a scripting API.
Hugging Face model
Open source ↗This is a machine learning model repository on Hugging Face containing an EXL3 quantization of dealignai/GLM-5.3-UNCENSORED-FP8. That base model is a weight-edited variant, not a fine-tune, of zai-org/GLM-5.3, with the edit documented in a file named CRACK SURGERY.json. The repository states it is not affiliated with dealignai or Z.ai.
Hugging Face model
Open source ↗Decision-2.0-Vega-27B is a 27B-parameter decision model that is part of Decision 2.0, the decision models of vLLM Semantic Router. It takes an input in text or JSON form along with questions to answer, such as picking one of several options, saying yes or no, or rating on a scale. It answers all of the questions at once and returns a probability for every answer.
Hugging Face model
Open source ↗Origin Lab Game Recordings v0.4.0 is a dataset of human gameplay recorded inside the engines of 20 licensed games at 1080p and 60 FPS. Each recording includes RGB frames with and without the HUD, depth, surface normals, camera pose, keyboard and mouse input, in-engine events and game state, and audio. This release doubles the roster to 20 games and adds the first Unity title, with 169 sessions totaling 163.0 hours and a size of about 5.3 TB.
Hugging Face dataset
Open source ↗GLiNER2.5-Decide is a 340M-parameter English text classification model in the GLiNER2.5 family. Instead of using a fixed prompt template, it accepts any label set at call time, covering uses such as intent, routing, sentiment, priority, policy, and multi-label tagging, all in a single forward pass without generating tokens. It can be loaded with AutoExtractor and run locally.
Hugging Face model
Open source ↗Get early signals on the websites, apps, repositories and startups gaining momentum. Join the list for Risefinder email briefings.
By subscribing, you ask us to store your email and send Risefinder updates. You can unsubscribe at any time. Privacy.
Want a sample first? Read past daily emails.