Arzu CanerAI DevCamp Notes: Deep Learning (Week 3)In Week 3 of AlDev Camp, we delved into deep learning, building on the data and concepts covered in the first two weeks to make this…Jul 11
Eduardo OrdaxFine tuning Vs Pre-trainingThe objective of my articles is to ensure clarity and simplicity in technical explanations. To achieve this, I will skip over certain…Jan 15
Subrata GoswamiPre-training Mini Versions of LLMs — GPT and Llama3This blog goes over how to pre-train small versions of the leading open source Large Language Models (LLM). Here 3 models are covered — 2…Jun 17Jun 17
Anastasia TzevelekaLLM domain adaptation using continued pre-training — Part 3/4Exploring domain adaptation via continued pre-training for large language models (LLMs)? This 4-part series answers the most common…May 9May 9
Vivek MadanLLM End-to-End & Resources Part 2 — Pre-trainingIn the previous post, we saw the model architecture recipe for large language models. In this post, we will discuss the first stage of…Jun 3Jun 3
Arzu CanerAI DevCamp Notes: Deep Learning (Week 3)In Week 3 of AlDev Camp, we delved into deep learning, building on the data and concepts covered in the first two weeks to make this…Jul 11
Eduardo OrdaxFine tuning Vs Pre-trainingThe objective of my articles is to ensure clarity and simplicity in technical explanations. To achieve this, I will skip over certain…Jan 15
Subrata GoswamiPre-training Mini Versions of LLMs — GPT and Llama3This blog goes over how to pre-train small versions of the leading open source Large Language Models (LLM). Here 3 models are covered — 2…Jun 17
Anastasia TzevelekaLLM domain adaptation using continued pre-training — Part 3/4Exploring domain adaptation via continued pre-training for large language models (LLMs)? This 4-part series answers the most common…May 9
Vivek MadanLLM End-to-End & Resources Part 2 — Pre-trainingIn the previous post, we saw the model architecture recipe for large language models. In this post, we will discuss the first stage of…Jun 3
maadaa.aiUnderstanding Multimodal LLMs and Video Language Pre-training: Key Progress, Applications, Methods…How to utilize the video and corresponding weak captions to perform representation learning has recently become a hot topic.Mar 14
Abdullah Şamil GüserCLIP: Contrastive Language-Image PretrainingPaper by Alec Radford, Ilya Sutskever et al. from OpenAIMay 5
AmanpreetsinAi2 BlogSPECTER2: Adapting Scientific Document Embeddings to Multiple Fields and Task FormatsSPECTER2, a new scientific embedding model trained on 9 tasks across classification, regression and retrieval.Nov 27, 2023