Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 59 for “"parameter efficient fine-tuning"”.

  1. Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks

    … due to the high computational costs of fine-tuning large language models. This thesis explores two different parameter-efficient fine-tuning methods for training large language models to mimic watermarked models. These methods are: (i) the low rank adaptations and (ii) transfer learning. …

    tamu Repository record for Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks (opens in a new tab)

  2. Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks

    … due to the high computational costs of fine-tuning large language models. This thesis explores two different parameter-efficient fine-tuning methods for training large language models to mimic watermarked models. These methods are: (i) the low rank adaptations and (ii) transfer learning. …

    tamu Repository record for Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks (opens in a new tab)

  3. Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks

    … due to the high computational costs of fine-tuning large language models. This thesis explores two different parameter-efficient fine-tuning methods for training large language models to mimic watermarked models. These methods are: (i) the low rank adaptations and (ii) transfer learning. …

    tamu Repository record for Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks (opens in a new tab)

  4. Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks

    … due to the high computational costs of fine-tuning large language models. This thesis explores two different parameter-efficient fine-tuning methods for training large language models to mimic watermarked models. These methods are: (i) the low rank adaptations and (ii) transfer learning. …

    tamu Repository record for Parameter-Efficient Fine-Tuning for Learning Language Model Watermarks (opens in a new tab)

  5. Optimizing Transformer Models: From Isotropic Architectural Design to Parameter-Efficient Fine-Tuning for Large-Scale NLP

    … words, e!ciency is not only a question of saving parameters or reducing FLOPs, but also a question of avoiding representational pathologies that waste capacity by collapsing variation. This motivates a representational viewpoint in which the geometry of contextual embedding spaces is treated as a …

    ulpgc Repository record for Optimizing Transformer Models: From Isotropic Architectural Design to Parameter-Efficient Fine-Tuning for Large-Scale NLP (opens in a new tab)

  6. Parameter-efficient fine-tuning for software engineering : a systematic study of low-resource and multilingual knowledge transfer

    … languages remains computationally expensive. Parameter-Efficient Fine-Tuning (PEFT) methods address this challenge by updating only a small subset of parameters or introducing lightweight adaptation modules. However, there is limited empirical understanding of how different PEFT methods behave …

    ubc Repository record for Parameter-efficient fine-tuning for software engineering : a systematic study of low-resource and multilingual knowledge transfer (opens in a new tab) Download PDF for Parameter-efficient fine-tuning for software engineering : a systematic study of low-resource and multilingual knowledge transfer (opens in a new tab)

  7. Interpretable and Efficient Music Harmonic Analysis Using Multilinear Mixture of Experts and Parameter-Efficient Fine-Tuning Methods

    Σκοπός της παρούσας διπλωματικής εργασίας είναι η μελέτη της αυτόματης ανάλυσης αρμονίας με ρωμαϊκούς αριθμούς (Roman Numeral Analysis) στο πεδίο της ανάκτησης μουσικής πληροφορίας (Music Information Retrieval) και πώς αυτή μπορεί να βελτιωθεί βάσει της αποδοτικότητας και της ερμηνευσιμότητας. Τα …

    athens Repository record for Interpretable and Efficient Music Harmonic Analysis Using Multilinear Mixture of Experts and Parameter-Efficient Fine-Tuning Methods (opens in a new tab)

  8. ScPEFT : a parameter-efficient fine-tuning framework for enhancing single-cell large language models in out-of-context

    … To address this, we introduce a single-cell parameter-efficient fine-tuning (scPEFT) framework that integrates learnable, low-dimensional adapters into scLLMs. By freezing the backbone model and updating only the adapter parameters, scPEFT efficiently adapts to specific tasks using limited …

    missouri Repository record for ScPEFT : a parameter-efficient fine-tuning framework for enhancing single-cell large language models in out-of-context (opens in a new tab)

  9. Training a massively multimodal transformer on YouTube data: pre-training and parameter efficient fine-tuning on HPC infrastructure

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms

    uiuc Repository record for Training a massively multimodal transformer on YouTube data: pre-training and parameter efficient fine-tuning on HPC infrastructure (opens in a new tab)

  10. Closed Domain Question Answering With Language Models: Application of Retrieval-Augmented Generation and Parameter Efficient Fine-Tuning In Healthcare

    … Retrieval-Augmented Generation (RAG) with Parameter-Efficient Fine-Tuning (PEFT) to create a scalable, efficient, and domain-specific solution. By leveraging structured datasets of dementia-related question-answer pairs and integrating advanced techniques like context injection and model …

    kennesaw Repository record for Closed Domain Question Answering With Language Models: Application of Retrieval-Augmented Generation and Parameter Efficient Fine-Tuning In Healthcare (opens in a new tab)

  11. Design and implementation of a parameter-efficient fine-tunning website for pre-defined ai model /

    … software engineering challenges associated with parameter-efficient fine-tuning (PEFT) of large language models, particularly the complexity, cost and inefficiency of manual experimentation. The main contribution is the design and implementation of a web-based tool that helps researchers and …

    vilnius Repository record for Design and implementation of a parameter-efficient fine-tunning website for pre-defined ai model / (opens in a new tab)

  12. DYNAMIC NEURAL NETWORKS FOR EFFICIENT VISION MODEL INFERENCE

    … is hindered by high training overhead from full-parameter fine-tuning and limited application beyond visual perception. This thesis addresses these challenges through three key contributions: Parameter-Efficient Fine-Tuning (PEFT): We demonstrate that dynamic networks can be developed with …

    nus Repository record for DYNAMIC NEURAL NETWORKS FOR EFFICIENT VISION MODEL INFERENCE (opens in a new tab) Download file for DYNAMIC NEURAL NETWORKS FOR EFFICIENT VISION MODEL INFERENCE (opens in a new tab)

  13. INVESTIGATION INTO THE DUALITY OF CONTEXT PROMPTS AND LARGE LANGUAGE MODEL WEIGHTS

    … suggests a deep connection between context and parameters. This thesis formalizes that link, showing that ICL in a single linear attention layer equals one gradient-descent step on an analytically defined dataset, and in multi-layer networks acts as a greedy layer-wise training process. We then …

    nus Repository record for INVESTIGATION INTO THE DUALITY OF CONTEXT PROMPTS AND LARGE LANGUAGE MODEL WEIGHTS (opens in a new tab) Download file for INVESTIGATION INTO THE DUALITY OF CONTEXT PROMPTS AND LARGE LANGUAGE MODEL WEIGHTS (opens in a new tab)

  14. Efficient Fine-Tuning of Foundation Models: Generalization, Disparity, and Subgroup Adaptation

    … First, it studies demographic adaptation with parameter-efficient fine-tuning (PEFT) under realistic constraints where full fine-tuning is infeasible and available data are skewed. We evaluate five adaptation strategies, three pretraining paradigms, and multiple medical imaging datasets, …

    york Repository record for Efficient Fine-Tuning of Foundation Models: Generalization, Disparity, and Subgroup Adaptation (opens in a new tab)

  15. TASK-ORIENTED DIALOGUE UNDERSTANDING AND EVALUATION USING MINIMAL DATA

    … TOD-specific automated data augmentation, and a Parameter-Efficient Fine-Tuning (PEFT) method, aimed at enhancing system adaptability to new domains. It also proposes a novel evaluation metric, Granular Change Accuracy (GCA), offering a more precise assessment of DST model performance and …

    nus Repository record for TASK-ORIENTED DIALOGUE UNDERSTANDING AND EVALUATION USING MINIMAL DATA (opens in a new tab) Download file for TASK-ORIENTED DIALOGUE UNDERSTANDING AND EVALUATION USING MINIMAL DATA (opens in a new tab)

  16. Retrieval-augmented speech-based question answering system

    … odpovídání na otázky nad dlouhým audiem, zatímco parameter-efficient fine-tuning pomocí LoRA adaptérů dále zvyšuje přesnost na benchmarku. Dodatečná analýza však ukazuje, že model se často více spoléhá na interní jazykové znalosti než na informace obsažené ve vyhledaném audiu. Výsledky práce …

    brno-tech Repository record for Retrieval-augmented speech-based question answering system (opens in a new tab)

  17. Domain-Aware Reasoning with Lightweight Models via Knowledge Distillation

    … and RAG-retrieved context, the student model was fine-tuned via Supervised Fine-Tuning (SFT) on the teacher’s generated reasoning chains, employing Parameter-Efficient Fine-Tuning (PEFT) with Low-Rank Adaptation (LoRA). Comprehensive evaluation, incorporating both AI-assisted analysis and blind …

    chalmers Repository record for Domain-Aware Reasoning with Lightweight Models via Knowledge Distillation (opens in a new tab)

  18. Efficient inference and adaptation in deep learning : from edge systems to large language models

    … research problem.This thesis investigates efficient inference, training, and adaptation in DL across the model lifecycle from four complementary perspectives: (1) enabling lightweight and energy-efficient inference of DL models on edge devices and distributed Internet of Things (IoT) …

    lund Repository record for Efficient inference and adaptation in deep learning : from edge systems to large language models (opens in a new tab) Download PDF for Efficient inference and adaptation in deep learning : from edge systems to large language models (opens in a new tab)

  19. Automatic Generation of vTESTstudio Test Cases from Natural Language Requirements Using Large Language Models

    … further studies retrieval-based grounding, parameter-efficient fine-tuning for intermediate representation generation, and retrieved skill guidance for improving logical planning. On the small evaluation sets used in this thesis, the proposed pipeline produced useful test artefacts in …

    chalmers Repository record for Automatic Generation of vTESTstudio Test Cases from Natural Language Requirements Using Large Language Models (opens in a new tab)

Page 1 of 3