Yashu GuptaUnderstanding Flash Attention - Fueling Large language ModelsDetailed Understanding of Flash Attention which is getting widely used in many of the Large Language Models.6 min read·Jul 25, 2023----
Yashu GuptaQLORA: Efficient Finetuning of Large Language Model (Falcon 7B) using Quantized Low Rank AdaptersFinetuning open source Large Language Models like Falcon 7B on domain data with less than 15 GB of VRAM GPU using Quantization of Low Rank…8 min read·Jun 21, 2023--2--2
Yashu GuptaLangChain-Supercharging Large Language Models With LC and Vector DBBuilding Document Question Answering using LLM, Langchain, Pinecone, Croma 🔗5 min read·Apr 26, 2023----
Yashu GuptainNerd For TechChat GPT and GPT 3 Detailed Architecture Study-Deep NLP HorseA detailed intuition and methodology behind the GPT and Chat GPT Language Models.9 min read·Mar 2, 2023--2--2
Yashu GuptaFaster Inference for NLP Pipeline’s using Hugging Face Transformers and ONNX RuntimeTransformers are taking the NLP world by storm as it is a powerful engine in understanding the context. Nowadays with use of Transformers…3 min read·Jan 3, 2021----
Yashu GuptaIn and Out of Transformers (Attention is all you need) -Deep NLP HorseTransformer Introduction and In Depth Tutorial |Zero to Hero in Modern NLP with Transformer11 min read·Aug 26, 2020----