The article discusses building a multi-model finance drama using small models, involving the collaboration of five labs. This work explores the application of multiple AIs to create a financial "drama".
This paper introduces the "constraint tax," a measurement protocol to quantify the loss in answer accuracy caused by structured output constraints on Small Language Models (SLMs). It demonstrates that for SLMs, imposing such constraints improves schema validity but can compromise the correctness of the underlying answer.
This content provides a curated overview of the top small language models currently on Hugging Face. It details their specific strengths, supporting benchmark data, and includes code examples for implementation.
This research presents a locally deployable framework enabling small language models to extract privacy-sensitive clinical entities from unstructured dental notes through self-generated and refined prompts. The study evaluated open-weight models, achieving high F1 scores with Qwen2.5-14B-Instruct and Llama-3.1-8B-Instruct after supervised fine-tuning and direct preference optimization.
This research introduces Terminus-4B, a finetuned small language model, to explore its capability in replacing frontier LLMs for agentic terminal execution tasks. The model is post-trained using Supervised Finetuning and Reinforcement Learning with rubric-based LLM-as-judge rewards.
This content explores the concept of building AI agents using local small language models. It challenges the traditional view that only large tech companies can develop such advanced AI solutions.
