Shivansh KaushikImplementing Large Multimodal Models (LMM) in few lines of code using Langchain and OllamaWhat are LMMs?Apr 11Apr 11
Shivansh KaushikFunction calling agents with Hermes-2 Pro LocallyUtilizing function-calling capability of Hermes-2 Pro to build autonomous agents and unleashing the power of open-source LLMs!Mar 20Mar 20
Shivansh KaushikAdvanced Text Retrieval with Elasticsearch & LlamaIndex: Sentence Window RetrievalExplore Advanced Text Retrieval with Elasticsearch & LlamaIndex, focusing on Sentence Window Retrieval (SWR) for precision and efficiency.Jan 112Jan 112
Shivansh KaushikMultimodal Agent: Image Captioning with Mistral 7B on CPURun a large language model on your CPU and build custom agents to caption images!Dec 1, 20232Dec 1, 20232
Shivansh KaushikThis technique will make your LLM Smarter and more Context-Aware: RAG on SteroidsUsing Reciprocal Rank Fusion and Query Generation to enhance the power of Retrieval Augmented GenerationOct 31, 20231Oct 31, 20231
Shivansh KaushikEfficient Model Fine-Tuning for LLMs: Understanding PEFT by ImplementationFine-tuning large language models (LLMs) is a computationally intensive process, posing challenges in terms of memory requirements and time…Jul 31, 2023Jul 31, 2023
Shivansh KaushikThe No BS Guide to LLMs: A Primer for ML EnthusiastsThe recent AI revolution has brought about groundbreaking advancements in Natural Language Processing (NLP) and Machine Learning (ML)…Jul 18, 20231Jul 18, 20231