Search Results for "multiple choice"

Kev is a family of open decision models inspired by Jev and built on Qwen3.5 and Qwen3.8 foundations. It processes a document together with multiple typed questions and returns probabilities instead of generated prose. Supported question formats include yes-or-no, multiple choice, and ordered scoring. Checkpoints range from a compact 0.8B model for smaller hardware to a 27B version for high-end systems. The models include probability calibration and can run through CUDA, ROCm, or MLX depending on hardware. ...

...Its first model has 1.9 billion parameters and replaces the language-modeling head of Qwen3.5-2B-Base with a small pointer-based decision head. It supports yes-or-no, multiple-choice, and score questions while returning calibrated confidence values. Shared-prefix caching makes multiple questions about the same state inexpensive. The package includes a CLI, HTTP server, training pipeline, evaluation tools, and a worked Strands Agents SDK integration. Inference runs on CUDA, CPU, Apple MPS, and MLX.

nanochat is a from-scratch, end-to-end “mini ChatGPT” that shows the entire path from raw text to a chatty web app in one small, dependency-lean codebase. The repository stitches together every stage of the lifecycle: tokenizer training, pretraining a Transformer on a large web corpus, mid-training on dialogue and multiple-choice tasks, supervised fine-tuning, optional reinforcement learning for alignment, and finally efficient inference with caching. Its north star is approachability and speed: you can boot a fresh GPU box and drive the whole pipeline via a single script, producing a usable chat model in hours and a clear markdown report of what happened. ...

...Rather than focusing on a single metric or domain, it aggregates many hand-authored tasks that test reasoning, commonsense, math, linguistics, ethics, and creativity. Tasks are intentionally heterogeneous: some are multiple-choice with exact scoring, others are free-form generation judged by model-based or human evaluation. The suite provides a common JSON task format and an evaluation harness so research groups can contribute new tasks and reproduce results consistently. It emphasizes robustness analysis—looking at scale trends, calibration, and areas where models systematically fail—to guide model development beyond raw accuracy. ...

...Access your agents through a graphical user interface. Interact with agents by giving them input, permissions, etc. Agents typically learn and improve their performance over time with feedback loops. Run multiple agents simultaneously to improve efficiency and productivity. Connect to multiple Vector DBs to enhance your agent’s performance. Each agent is unique, use different models of your choice. Get insights into your agent’s performance and optimize accordingly. Control token usage to manage costs effectively. Enable your agents to learn and adapt by storing their memory. ...

...No black box: you can see exactly how the data is processed, and how the model is constructed, and you can make tweaks as necessary. automl-gs is an AutoML tool which, unlike Microsoft's NNI, Uber's Ludwig, and TPOT, offers a zero code/model definition interface to getting an optimized model and data transformation pipeline in multiple popular ML/DL frameworks, with minimal Python dependencies (pandas + scikit-learn + your framework of choice). automl-gs is designed for citizen data scientists and engineers without a deep statistical background under the philosophy that you don't need to know any modern data preprocessing and machine learning engineering techniques to create a powerful prediction workflow.