9 results found Sort:

arcee-ai
mergekit arcee-ai
434
4.8k
lgpl-3.0
52
Tools for merging pretrained large language models.
llm llama model-merging
Created 2023-08-21
214 commits to main branch, last one 7 days ago
EnnengYang
Awesome-Model-Merging-Methods-Theories-Applications EnnengYang
7
199
unknown
4
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666.
llms robustness model-fusion meta-learning model-merging attack-defense generalization diffusion-models generative-model knowledge-fusion ensemble-learning few-shot-learning foundation-models transfer-learning continual-learning federated-learning zero-shot-learning multi-task-learning large-language-models multi-domain-learning
Created 2024-06-19
106 commits to main branch, last one a day ago
bloomberg
dataless-model-merging bloomberg
5
84
apache-2.0
7
Code release for Dataless Knowledge Fusion by Merging Weights of Language Models (https://openreview.net/forum?id=FCnohuR6AnM)
model-merging language-model
Created 2023-02-27
1 commits to main branch, last one about a year ago
tanganke
fusion_bench tanganke
9
81
mit
4
FusionBench: A Comprehensive Benchmark/Toolkit of Deep Model Fusion
model-fusion model-mixing model-merging multi-tasking model-ensemble deep-neural-networks large-language-models machine-learning-algorithms
Created 2024-05-13
350 commits to main branch, last one 5 days ago
zhangyikaii
LAMDA-ZhiJian zhangyikaii
2
50
mit
3
ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse
toolbox model-reuse model-merging regularization pre-trained-model knowledge-distillation parameter-efficient-tuning
Created 2023-07-13
42 commits to main branch, last one about a year ago
EnnengYang
AdaMerging EnnengYang
2
49
mit
3
AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.
model-fusion model-editing model-merging multi-task-learning test-time-adaptation
Created 2023-09-29
34 commits to main branch, last one 10 days ago
nik-dim
tall_masks nik-dim
0
34
mit
3
Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
model-merging task-arithmetic
Created 2024-04-29
23 commits to master branch, last one 13 days ago
declare-lab
della declare-lab
2
27
unknown
0
DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
llm llms huggingface transformer model-merging
Created 2024-06-17
5 commits to main branch, last one 3 months ago
EnnengYang
RepresentationSurgery EnnengYang
3
27
mit
3
Representation Surgery for Multi-Task Model Merging. ICML, 2024.
model-fusion model-editing model-merging multi-task-learning
Created 2024-02-04
15 commits to main branch, last one 28 days ago