https://github.com/avnlp/llm-blender

Ensembling LLMs using LLM-Blender

llm-blender rag rankers

Last synced: 12 Jan 2025

https://github.com/avnlp/rrf

Performance Evaluation of Rankers and RRF Techniques for Retrieval Pipelines

diversity-ranker lost-in-the-middle-ranker ranker reciprocal-rank-fusion rrf similarity-ranker

Last synced: 12 Jan 2025

https://github.com/avnlp/finrag

corrective-rag crag earnings-calls finance pinecone rag self-rag self-reflective-rag

Last synced: 12 Jan 2025

https://github.com/avnlp/llm-finetuning

fine-tuning lora p-tuning peft qlora sft

Last synced: 13 Apr 2025

https://github.com/avnlp/rankers

listwise llm-rankers pairwise pointwise ranker setwise

Last synced: 04 Apr 2025

https://github.com/avnlp/dataloaders

Last synced: 12 Jan 2025

https://github.com/avnlp/vectordb

Created pipelines for Semantic Search, Metadata Filtering, Hybrid Search, Reranking, and Retrieval-Augmented Generation (RAG) for the TriviaQA, ARC, PopQA, FactScore, and Edgar datasets. These pipelines have been implemented for the Pinecone, Weaviate, Milvus, Qdrant and Chroma vector databases.

haystack langchain llm milvus pinecone vector-database weaviate

Last synced: 11 Apr 2025

https://github.com/avnlp/rag-pipelines

Advanced RAG Pipelines and Evaluation: Self-Reflective RAG, Corrective RAG, Adaptive RAG, Sub-Query Generation and Routing, DSPy, DeepEval

crag deepeval dspy llm pinecone rag self-rag

Last synced: 13 May 2025

https://github.com/avnlp/hyperparameter-tuning

Effect of Optimizer Selection and Hyperparameter Tuning on Training Efficiency and LLM Performance

adam-optimizer hyperparameter-tuning optimizers rmsprop-optimizer sgd-momentum sgd-optimizer

Last synced: 12 Jan 2025

https://github.com/avnlp/finbert-hf

Last synced: 01 Mar 2025

https://github.com/avnlp/.github

Last synced: 01 Mar 2025