Categories | LEE

Light

Dark

CV

Mar 30, 2023 Everything you need to know about Few-Shot Learning
Jan 05, 2022 mAP
Jan 05, 2022 The idea you need to understand about the Object Detection Model

Developing

Nov 20, 2024 vllm + lm-evaluation-harness OOM
Nov 15, 2024 vLLM error - gemma계열 모델에서 발생하는 오류
Nov 11, 2024 Solving Docker Connection Issues with OpenWebUI and Ollama Models
Feb 08, 2024 Compare to Activation Function
Jan 24, 2024 TypeError - TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]]
Nov 30, 2023 When fine-tuning LLM with a transformer, encountering OOM (Out of Memory) errors
Nov 22, 2023 Change model input sequence length
Nov 16, 2023 OOM error solution - Llama2 70b
Oct 20, 2023 Implementation on Text-Generation Inference (TGI)
Oct 11, 2023 docker - error response from daemon could not select device driver "" with capabilities [[gpu]]
Sep 25, 2023 netplan - No module named 'netifaces'
Sep 13, 2023 가상환경 이슈 - Command '['/home/ubuntu/test/bin/python3', '-m', 'ensurepip', '--upgrade', '--default-pip']' returned non-zero exit status 1.
Sep 08, 2023 Pytorch에서 CUDA 및 그래픽카드 인식 문제 - Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error?
Sep 01, 2023 그래픽드라이버 버젼 이슈
Aug 09, 2023 Connect to server in VSCode
Aug 01, 2023 Daily of Developing [8/1]
Jul 29, 2023 Daily of Developing [7/29]
Jul 27, 2023 Daily of Developing [7/27]
Jul 18, 2023 Daily of Developing [7/21]
Jul 18, 2023 Daily of Developing [7/20] - Repo id must be in the form 'repo_name' or 'namespace/repo_name'
Jul 18, 2023 Daily of Developing [7/19]
Jul 17, 2023 Daily of Developing [7/17]

Finetuning

Aug 22, 2023 LoRA Error - "expected scalar type Half but found Float"
Aug 08, 2023 PEFT's Target Modules Mappings
Aug 07, 2023 IA3
Jul 13, 2023 Transformers TrainingArguments' Hyperparameters
Jul 11, 2023 QLoRA 파인튜닝 - trouble shooting 및 일지
Jul 05, 2023 파인튜닝 과정에서 습득한 지식들
Apr 12, 2023 Training for DeepSpeed and FairScale

NLP

Nov 12, 2024 (LLM-University) 1-4. Reranking
Nov 10, 2024 (LLM-University) 1-3. Dense Retrieval
Nov 09, 2024 (LLM-University) 1-2. Keyword Search
Oct 29, 2024 (LLM-University) 1-1. What is Semantic Search?
Mar 29, 2024 PEFT new features
Mar 01, 2024 PEFT new features
Jan 18, 2024 Message History
Oct 30, 2023 CUDA error - device-side assert triggered Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
Jun 09, 2023 LoRA peft 파인튜닝
May 31, 2023 Bard API 사용 이슈
May 24, 2023 Polyglot-ko model FT via LoRA
May 23, 2023 Polyglot-ko 모델 파인튜닝
May 18, 2023 DeepSpeed Finetuning시 마주한 에러들
Apr 17, 2023 Prompt Engineering
Apr 05, 2023 Terms in NLP
Mar 31, 2023 Zero-Shot Learning in NLP
Feb 02, 2023 Few shot learning in NLP from text classification task

PaperReview

Jun 19, 2024 Outrageously large neural networks - the sparsely-gated mixture-of-experts layer [2017]
Jun 19, 2024 Chat Vector - A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages [2024]
May 03, 2024 Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing (AlphaLLM) [2024]
Apr 30, 2024 DoRA - Weight Decomposed Low-Rank Adaptation [2024]
Apr 25, 2024 VERA - Vector Based Random Matrix Adaptation [2024]
Dec 29, 2023 The Power of Scale for Parameter-Efficient Prompt Tuning [2021]
Dec 19, 2023 EDA - Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks [2019]
Dec 14, 2023 Ziya2 - Data-centric Learning is All LLMs Need [2023]
Dec 07, 2023 LoftQ - LoRA-Fine-Tuning-Aware Quantization for Large Language Models [2023]
Aug 07, 2023 IA3 - Few-shot Parameter-Efficient Fine-tuning is better and cheaper than In-Context Learning [2022]
Jul 12, 2023 QLORA - Efficient Finetuning of Quantized LLMs [2023]
Jul 10, 2023 BEiT - BERT Pre-Training of Image Transformers [2022]
Jun 29, 2023 ConvNeXt - A ConvNet for the 2020s [2022]
Jun 28, 2023 ResNeXt - Aggregated Residual Transformations for Deep Neural Networks [2017]
Jun 23, 2023 EfficientNetV2 - Smaller Models and Faster Training [2021]
Jun 21, 2023 EfficientNet - Rethinking Model Scaling for Convolutional Neural Networks [2020]
Jun 01, 2023 FLAN - Finetuned Language Models Are Zero-Shot Learners [2021]
Apr 24, 2023 LoRA - Low-Rank Adaptation of Large Language Models [2021]
Apr 24, 2023 LLaMA - Open And Efficient Foundation Language Models [2023]
Apr 21, 2023 CoT - Chain-of-Thought Prompting Elicits Reasoning in Large Language Models [2023]
Jan 20, 2023 GPT3 - Language Models Are Few-Shot Learners [2020]
Mar 14, 2022 SwinTransformer - Hierarchical Vision Transformer using Shifted Windows
Feb 27, 2022 ViT - An Image is Worth 16x16 Words Transformers for Image Recognition at Scale [2020]
Jan 26, 2022 BERT - Pre-training of Deep Bidirectional Transformers for Language Understanding [2018]
Jan 13, 2022 RNN
Jan 13, 2022 LSTM - Long Short-Term Memory [1997]
Jan 13, 2022 ELMO - Deep contextualized word representations [2018]
Jan 12, 2022 OHEM - Training Region-based Object Detectors with Online Hard Example Mining [2016]
Jan 11, 2022 Overfeat - Integrated Recognition, Localization and Detection using Convolutional Networks [2013]
Jan 10, 2022 Faster R-CNN - Towards Real-Time Object Detection with Region Proposal Networks [2015]
Jan 07, 2022 Fast R-CNN [2015]
Jan 06, 2022 R-CNN - Rich feature hierarchies for accurate object detection and semantic segmentation [2013]
Jan 04, 2022 Yolo v1 - You Only Look Once Unified, Real-Time Object Detection [2015]
Jan 04, 2022 Transformer - Attention Is All You Need [2017]

python

Oct 08, 2024 vllm - when loading the weights, occurs infinite loading problem
Sep 12, 2024 python enum
Sep 11, 2024 python enumerate function
Sep 10, 2024 python map function
Sep 01, 2024 pytest
Aug 22, 2024 python abstract class
Feb 22, 2024 pip 설치 옵션
Feb 18, 2024 torch tensor manipulation3
Jan 11, 2024 Utilizing Variable Arguments in Python - args and kwargs
Jan 04, 2024 정규표현식으로 텍스트 전처리
Nov 10, 2023 torch tensor manipulation2
Nov 03, 2023 torch tensor manipulation1
Oct 02, 2023 DB 접속 오류 - You have an error in your SQL syntax; check the manual that corresponds to your MariaDB server version for the right syntax to use near
Jun 14, 2023 Typing 모듈 - 타입 어노테이션
Feb 05, 2023 가정 설명문