3 results found Sort:

microsoft
unilm microsoft
2.4k
19.1k
mit
297
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
1,180 commits to master branch, last one about a month ago
gokayfem
awesome-vlm-architectures gokayfem
11
164
cc0-1.0
7
Famous Vision Language Models and Their Architectures
vlm blip clip llava cogvlm kosmos awesome qwen-vl internlm multimodal awesome-list text-encoder image-encoder vision-language-model
Created 2024-02-15
221 commits to main branch, last one 14 days ago
kyegomez
Kosmos2.5 kyegomez
6
64
mit
2
My implementation of Kosmos2.5 from the paper: "KOSMOS-2.5: A Multimodal Literate Model"
gpt3 gpt4 kosmos attention multimodal opensource multi-modality multimodal-deep-learning attention-is-all-you-need
Created 2023-09-22
29 commits to main branch, last one 7 months ago