AI (105) 썸네일형 리스트형 [KoT-platypus2] - CoT + KO-platypus2 HuggingFace: https://huggingface.co/kyujinpy/KoT-platypus2-7B kyujinpy/KoT-platypus2-7B · Hugging Face KoT-platypus2 CoT + KO-platypus2 = KoT-platypus2 Model Details Model Developers Kyujin Han (kyujinpy) Input Models input text only. Output Models generate text only. Model Architecture KoT-platypus2-7B is an auto-regressive language model based on the LLaM huggingface.co Github: https://github... [CoT-llama2] - Chain-of-thought 방식을 활용하여 llama2-ko를 fine-tuning HuggingFace: https://huggingface.co/kyujinpy/CoT-llama-2k-7b kyujinpy/CoT-llama-2k-7b · Hugging Face CoT-llama2-7B More detail repo(Github): CoT-llama2 Model Details Model Developers Kyujin Han (kyujinpy) Input Models input text only. Output Models generate text only. Model Architecture CoT-llama2 is an auto-regressive language model based on the LLaMA2 t huggingface.co Dataset: https://huggingf.. [9/28 오전 8시 리더보드 1등, 4등] Open KO-LLM 리더보드 후기 Leaderboard: Open Ko-LLM Leaderboard - a Hugging Face Space by upstage Open Ko-LLM Leaderboard - a Hugging Face Space by upstage huggingface.co KO-platypus: https://github.com/Marker-Inc-Korea/KO-Platypus GitHub - Marker-Inc-Korea/KO-Platypus: [KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platy [KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model.. [KO-Platy🥮] - Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model 🥮Github🥮: https://github.com/Marker-Inc-Korea/KO-Platypus GitHub - Marker-Inc-Korea/KO-Platypus: [KO-Platypus] Korean-Open-Platypus 번역 데이터셋을 활용한fine-tuning Platypus [KO-Platypus] Korean-Open-Platypus 번역 데이터셋을 활용한fine-tuning Platypus - GitHub - Marker-Inc-Korea/KO-Platypus: [KO-Platypus] Korean-Open-Platypus 번역 데이터셋을 활용한fine-tuning Platypus github.com 🥮Huggingface🥮: https://huggingface.co/kyujinp.. [Tune-A-VideKO] - 한국어 기반 One-shot Tuning of diffusion for Text-to-Video 모델 Github: https://github.com/KyujinHan/Tune-A-VideKO/tree/master GitHub - KyujinHan/Tune-A-VideKO: 한국어 기반 One-shot video tuning with Stable Diffusion 한국어 기반 One-shot video tuning with Stable Diffusion - GitHub - KyujinHan/Tune-A-VideKO: 한국어 기반 One-shot video tuning with Stable Diffusion github.com Tune-A-VideKO-v1-5🏄: https://huggingface.co/kyujinpy/Tune-A-VideKO-v1-5 kyujinpy/Tune-A-VideKO-v1-5 ·.. [KO-stable-diffusion-anything] - 한국어 기반의 stable-diffusion-disney와 KO-anything-v4-5 Github: https://github.com/KyujinHan/KO-stable-diffusion-anything GitHub - KyujinHan/KO-stable-diffusion-anything: Diffusion-based korean text-to-image generation model Diffusion-based korean text-to-image generation model - GitHub - KyujinHan/KO-stable-diffusion-anything: Diffusion-based korean text-to-image generation model github.com KO-anything-v4-5: https://huggingface.co/kyujinpy/KO-anythi.. [OpenFlaminKO] - Polyglot-KO를 활용한 한국어 기반 MultiModal 도전기! Github: https://github.com/Marker-Inc-Korea/OpenFlaminKO OpenFlamingo: https://github.com/mlfoundations/open_flamingo GitHub - mlfoundations/open_flamingo: An open-source framework for training large multimodal models. An open-source framework for training large multimodal models. - GitHub - mlfoundations/open_flamingo: An open-source framework for training large multimodal models. github.com Op.. [Tune-A-Video 논문 리뷰] One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation *Tune-A-Video를 위한 논문 리뷰 글입니다! 궁금하신 점은 댓글로 남겨주세요! Tune-A-Video paper: [2212.11565] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation (arxiv.org) Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T.. [DDIM 논문 리뷰] - DENOISING DIFFUSION IMPLICIT MODELS *DDIM를 위한 논문 리뷰 글입니다! 궁금하신 점은 댓글로 남겨주세요! DDIM paper: [2010.02502] Denoising Diffusion Implicit Models (arxiv.org) Denoising Diffusion Implicit Models Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present denoising d.. [DDPM 논문 리뷰] - Denoising Diffusion Probabilistic Models *DDPM를 위한 논문 리뷰 글입니다! 궁금하신 점은 댓글로 남겨주세요! DDPM paper: https://arxiv.org/abs/2006.11239 Denoising Diffusion Probabilistic Models We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound arxiv.org DDPM.. [DeepL] python을 이용한 한국어 번역 자동화 코드 (Not Pro and API. Using selenium) References: https://github.com/KyujinHan/Korean_selenium_DeepL GitHub - KyujinHan/Korean_selenium_DeepL: DeepL을 통한 한국 번역 자동화 코드 DeepL을 통한 한국 번역 자동화 코드. Contribute to KyujinHan/Korean_selenium_DeepL development by creating an account on GitHub. github.com # DeepL을 이용한 자동화 코드를 만들었습니다. # Api 필요없이, 단순 코드만 돌리면 바로 사용 가능합니다. # 기존에 있는 pip install {deep-cli, deepl, deepl-translate} 패키지들이 한국어를 지원하지 않고, 구글.. RuntimeError: Cannot writeback when the parameter shape changes 해당 에러는 모델을 돌리는 도중, backpropagation을 진행할 때 모델의 파라미터 shape이 같아야하는데 다를 때 일어나는 것이다. 에러를 어떻게 해결할까!? 일단 위의 system file을 따라서 위의 함수로 들어간다! if src_tensor is not None and src_tensor.shape != expected_shape: # NOTE: Gradient shape mismatch is not possible in practice since # the gradient shape is enforced to match that of the parameter and # we already check for parameter shape mismatch. raise RuntimeError.. 이전 1 2 3 4 5 6 7 ··· 9 다음
