본문 바로가기

전체 글

image-classification-on-imagenet https://paperswithcode.com/sota/image-classification-on-imagenet?p=resnest-split-attention-networks Papers with Code - ImageNet Benchmark (Image Classification) The current state-of-the-art on ImageNet is NoisyViT-B (384res, ImageNet-21k pretrain). See a full comparison of 958 papers with code. paperswithcode.com 더보기
프로젝트들 보는 사이트 https://www.producthunt.com/ Product Hunt – The best new products in tech. Product Hunt is a curation of the best new products, every day. Discover the latest mobile apps, websites, and technology products that everyone's talking about. www.producthunt.com 재미있는 것들 https://www.guidde.com/?ref=ph_home&utm_campaign=producthunt&utm_medium=ad&utm_source=producthunt guidde・Magically create video docum.. 더보기
QLora 구조 https://www.linkedin.com/posts/andrew-iain-jardine_llm-opensource-gpt3-activity-7153038508087984128-Qiqq?utm_source=share&utm_medium=member_android LinkedIn Andrew Jardine 페이지: #llm #opensource #gpt3 | 댓글 30 MoE ➕ QLoRA 🟰 PESC ......a new technique that turns any #LLM into a MoE LLM........ also we get a new #opensource model that beats Mixtral 🥳 The clever… | 댓글 30 www.linkedin.com 항상 댓글에 Lora와.. 더보기
다음 에러날때 Fatal Python error: init_import_site: Failed to import the site module Python runtime state: initialized Traceback (most recent call last): File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site.py", line 617, in main() File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site.py", line 604, in main known_paths = addsitepackages(known_paths) File "C:\Users\User\AppData\L.. 더보기
라마2 개선 버전? https://www.linkedin.com/posts/aiatmeta_introducing-prompt-engineering-with-llama-activity-7155984162926067712-PAAY?utm_source=share&utm_medium=member_android 더보기
Segmentation_models 대체제? https://www.linkedin.com/posts/merve-noyan-28b1a113a_many-cutting-edge-computer-vision-models-activity-7155609615504748544-puKA?utm_source=share&utm_medium=member_android 더보기
드림부스 finetune https://github.com/huggingface/autotrain-advanced GitHub - huggingface/autotrain-advanced: 🤗 AutoTrain Advanced 🤗 AutoTrain Advanced. Contribute to huggingface/autotrain-advanced development by creating an account on GitHub. github.com 더보기
양자학습법 - Mistral-7B https://www.linkedin.com/posts/akshay-pachaar_run-mistral-7b-almost-3x-faster-on-a-single-activity-7156262684999438336-mR0n?utm_source=share&utm_medium=member_android LinkedIn Akshay Pachaar 페이지: Run Mistral-7B almost 3x faster on a single GPU! Introducing AWQ:… | 댓글 14 Run Mistral-7B almost 3x faster on a single GPU! Introducing AWQ: Activation-aware Weight Quantization! 🚀 AWQ involves decreasi.. 더보기