0 bookmark(s) - Sort by: Date ↓ / Title /
The article introduces a new approach to language modeling called test-time scaling, which enhances performance by utilizing additional compute resources during testing. The authors present a method involving a curated dataset and a technique called budget forcing to control compute usage, allowing models to double-check answers and improve reasoning. The approach is demonstrated with the Qwen2.5-32B-Instruct language model, showing significant improvements on competition math questions.
This article provides a step-by-step guide on fine-tuning the Florence-2 model for object detection tasks, including loading the pre-trained model, fine-tuning with a custom dataset, and evaluating the model's performance.
A light-weight codebase that enables memory-efficient and performant finetuning of Mistral's models. It is based on LoRA, a training paradigm where most weights are frozen and only 1-2% additional weights in the form of low-rank matrix perturbations are trained.
"The paper introduces a technique called LoReFT (Low-rank Linear Subspace ReFT). Similar to LoRA (Low Rank Adaptation), it uses low-rank approximations to intervene on hidden representations. It shows that linear subspaces contain rich semantics that can be manipulated to steer model behaviors."
Introduces proxy-tuning, a lightweight decoding-time algorithm that operates on top of black-box LMs to achieve the same end as direct tuning. The method tunes a smaller LM, then applies the difference between the predictions of the small tuned and untuned LMs to shift the original predictions of the larger untuned model in the direction of tuning, while retaining the benefits of larger-scale pretraining.
First / Previous / Next / Last
/ Page 1 of 0