46 results found Sort:

microsoft
unilm microsoft
2.6k
20.2k
mit
308
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
llm nlp beit mllm trocr unilm xlm-e beit-3 bitnet kosmos minilm deepnet kosmos-1 layoutlm layoutxlm multimodal document-ai textdiffuser foundation-models pre-trained-model
Created 2019-07-23
1,216 commits to master branch, last one 11 days ago
thunlp
OpenPrompt thunlp
455
4.4k
apache-2.0
44
An Open-Source Framework for Prompt-Learning.
ai nlp prompt prompts pytorch nlp-library transformer deep-learning prompt-toolkit prompt-learning pre-trained-model prompt-based-tuning nlp-machine-learning natural-language-processing pre-trained-language-models natural-language-understanding
Created 2021-09-30
264 commits to main branch, last one about a year ago
brightmart
albert_zh brightmart
753
3.9k
unknown
103
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
bert xlnet albert pytorch roberta tensorflow pre-trained chinese-corpus pre-trained-model
Created 2019-09-26
107 commits to master branch, last one 2 years ago
ChineseGLUE
ChineseGLUE ChineseGLUE
247
1.8k
unknown
65
Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard
nlp bert glue albert datasets chinese-corpus pre-trained-model language-understanding
Created 2019-10-05
365 commits to master branch, last one 2 years ago
keyu-tian
SparK keyu-tian
84
1.5k
mit
26
[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling...
cnn mae ssl bert iclr convnet pytorch iclr2023 pretrain mask-rcnn pretraining deep-learning object-detection pre-trained-model masked-autoencoder sparse-convolution instance-segmentation masked-image-modeling self-supervised-learning convolutional-neural-networks
Created 2023-01-05
90 commits to main branch, last one 10 months ago
ymcui
Chinese-ELECTRA ymcui
171
1.4k
apache-2.0
26
Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）
nlp bert chinese electra pytorch tensorflow language-model chinese-electra pre-trained-model
Created 2020-03-23
51 commits to master branch, last one about a year ago
d-li14
involution d-li14
177
1.3k
mit
15
[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
pytorch cvpr2021 operator involution object-detection pre-trained-model image-classification instance-segmentation semantic-segmentation
Created 2021-01-29
26 commits to main branch, last one 3 years ago
zjunlp
KnowLM zjunlp
125
1.2k
mit
11
An Open-sourced Knowledgable Large Language Model Framework.
lora gpt-3 llama knowlm models chinese english bilingual deepspeed reasoning instructie instructions pre-training deep-learning language-model pre-trained-model instruction-tuning instruction-following large-language-models pre-trained-language-models
Created 2023-04-01
537 commits to main branch, last one 4 months ago
zjunlp
KnowledgeEditingPapers zjunlp
60
927
mit
27
Must-read Papers on Knowledge Editing for Large Language Models.
rome paper knowlm review survey easyedit paper-list awsome-list model-editing foundation-models knowledge-editing pre-trained-model large-language-models natural-language-processing pre-trained-language-models
Created 2022-12-06
241 commits to main branch, last one 20 hours ago
NVlabs
FasterViT NVlabs
62
789
other
17
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
coco ade20k backbone image-net deep-learning self-attention object-detection foundation-models pre-trained-model vision-transformer visual-recognition image-classification semantic-segmentation
Created 2023-05-19
275 commits to main branch, last one 5 months ago
MrGiovanni
ModelsGenesis MrGiovanni
140
737
other
15
[MICCAI 2019 Young Scientist Award] [MEDIA 2020 Best Paper Award] Models Genesis
3d-model fine-tuning foundation-models pre-trained-model transfer-learning representation-learning self-supervised-learning
Created 2019-07-24
271 commits to master branch, last one 9 months ago
deepmodeling
Uni-Mol deepmodeling
126
717
mit
17
Official Repository for the Uni-Mol Series Methods
pretraining deep-learning pre-trained-model molecular-modeling
Created 2022-05-22
144 commits to main branch, last one 28 days ago
salesforce
PCL salesforce
84
571
mit
17
PyTorch code for "Prototypical Contrastive Learning of Unsupervised Representations"
pre-trained-model contrastive-learning unsupervsied-learning representation-learning self-supervised-learning
Created 2020-07-28
48 commits to master branch, last one 2 years ago
mims-harvard
TFC-pretraining mims-harvard
81
440
mit
5
Self-supervised contrastive learning for time series via time-frequency consistency
time-series deep-learning pre-trained-model consistency-models contrastive-learning representation-learning self-supervised-learning
Created 2022-03-12
88 commits to main branch, last one about a year ago
NVlabs
GCVit NVlabs
48
425
other
10
[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
coco ade20k backbone imagenet pre-train deep-learning self-attention object-detection pre-trained-model vision-transformer visual-recognition semantic-segmentation imagenet-classification
Created 2022-06-18
113 commits to main branch, last one 11 months ago
edenai
edenai-apis edenai
58
421
apache-2.0
7
Eden AI: simplify the use and deployment of AI technologies by providing a unique API that connects to the best possible AI engines
ai api nlp ocr python aggregator speech-to-text text-to-speech ai-as-a-service computer-vision document-parsing image-processing pre-trained-model video-recognition speech-recognition machine-translation natural-language-processing optical-character-recognition
Created 2022-10-24
2,195 commits to master branch, last one 13 days ago
ymcui
PERT ymcui
24
354
apache-2.0
7
PERT: Pre-training BERT with Permuted Language Model
nlp plm bert pytorch tensorflow transformers pre-trained-model
Created 2022-01-04
22 commits to main branch, last one about a year ago
nogibjj
rust-mlops-template nogibjj
113
330
cc0-1.0
14
A work in progress to build out solutions in Rust for MLOPs
aws gil gpu onnx rust azure cloud mlops devops polars copilot pytorch actix-web tensorflow huggingface switchtorust devcontainers microservices mlops-workflow pre-trained-model
Created 2022-12-21
322 commits to main branch, last one about a year ago
HKUDS
UrbanGPT HKUDS
39
282
apache-2.0
15
[KDD'2024] "UrbanGPT: Spatio-Temporal Large Language Models"
smart-cities urban-computing fundation-models pre-trained-model instruction-tuning urban-data-science large-language-models spatio-temporal-prediction
Created 2024-02-21
34 commits to main branch, last one 9 days ago
hjbahng
visual_prompting hjbahng
30
267
mit
3
Exploring Visual Prompts for Adapting Large-Scale Models
pytorch prompt-tuning visual-prompting pre-trained-model transfer-learning
Created 2022-04-18
6 commits to main branch, last one 2 years ago
iflytek
MiniRBT iflytek
17
255
apache-2.0
7
MiniRBT (中文小型预训练模型系列)
bert pytorch roberta tensorflow pre-trained-model
Created 2022-11-15
10 commits to main branch, last one about a year ago
MrGiovanni
SuPreM MrGiovanni
8
253
other
4
[ICLR 2024 Oral] Supervised Pre-Trained 3D Models for Medical Image Analysis (9,262 CT volumes + 25 annotated classes)
dataset segmentation medical-imaging pre-trained-model transfer-learning
Created 2023-11-26
228 commits to main branch, last one 7 days ago
ZhangYuanhan-AI
NOAH ZhangYuanhan-AI
11
223
mit
2
[TPAMI] Searching prompt modules for parameter-efficient transfer learning.
pytorch deep-learning prompt-tuning visual-prompting pre-trained-model transfer-learning domain-generalization
Created 2022-06-06
57 commits to main branch, last one 11 months ago
rsommerfeld
trocr rsommerfeld
27
181
mit
5
Powerful handwritten text recognition. A simple-to-use, unofficial implementation of the paper "TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models".
ocr trocr transformer computer-vision pre-trained-model handwritten-text-recognition
Created 2022-02-08
12 commits to main branch, last one 2 years ago
YuanchenBei
Awesome-Pretraining-for-Graph-Neural-Networks YuanchenBei
11
172
mit
4
A curated list of papers on pre-training for graph neural networks (Pre-train4GNN).
graph fine-tuning pre-training graph-algorithms graph-pretraining pre-trained-model graph-neural-networks
Created 2023-04-27
45 commits to main branch, last one 9 months ago
YicongHong
Recurrent-VLN-BERT YicongHong
29
153
other
3
Code of the CVPR 2021 Oral paper: A Recurrent Vision-and-Language BERT for Navigation
bert cvpr2021 cvpr-oral transformer pre-trained-model vision-and-language vision-and-language-navigation
Created 2021-01-14
18 commits to main branch, last one 2 years ago
zjunlp
MolGen zjunlp
11
131
mit
7
[ICLR 2024] Domain-Agnostic Molecular Generation with Chemical Feedback
molgen pytorch selfies iclr2024 molecule multitask generation huggingface pre-training language-model pre-trained-model molecular-generation molecular-optimization pre-trained-language-models targeted-molecular-generation
Created 2023-01-04
74 commits to main branch, last one 6 months ago
HKUDS
HiGPT HKUDS
6
109
apache-2.0
2
[KDD'2024] "HiGPT: Heterogenous Graph Language Models"
graph-model graph-learning fundation-models pre-trained-model instruction-tuning graph-neural-networks large-language-models
Created 2024-02-18
20 commits to main branch, last one 5 months ago
siat-nlp
GALAXY siat-nlp
12
107
apache-2.0
2
Official repository of the AAAI'2022 paper "GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection"
semi-supervised pre-trained-model dialogue-generation task-oriented-dialogue
Created 2021-12-09
32 commits to main branch, last one 2 years ago
lyy1994
awesome-data-contamination lyy1994
2
76
mit
2
The Paper List on Data Contamination for Large Language Models Evaluation.
llm evaluation paper-list awesome-list foundation-models pre-trained-model data-contamination large-language-models pre-trained-language-models
Created 2024-01-02
47 commits to main branch, last one 2 days ago