AVNLP
Change the repository type filter
All
Repositories list
24 repositories
rankers
PublicModular LLM ranking library for Information Retrieval and RAG. Implements state-of-the-art Pairwise, Setwise, and Listwise ranking with structured generation and specialized models (RankZephyr, RankLlama). Features efficient sorting algorithms, sliding windows, and zero-shot capabilities.llm-blender
PublicLLM-Blender: Ensembling framework that maximizes LLM performance via pairwise ranking. Employs PairRanker to rank candidates and GenFuser to merge outputs, generating superior responses by combining the diverse strengths of multiple open-source models.rag-model-training
PublicTraining code for advanced RAG techniques - Adaptive-RAG, Corrective RAG, RQ-RAG, Self-RAG, Agentic RAG, and ReZero. Reproduces paper methodologies to fine-tune LLMs via SFT and GRPO for adaptive retrieval, corrective evaluation, query refinement, self-reflection, and agentic search behaviors.rag-pipelines
PublicAdvanced RAG Pipelines and Evaluationrrf
PublicPerformance Evaluation of Rankers and RRF Techniques for Retrieval Pipelines: Employs Diversity, Lost-in-the-Middle, and Similarity rankers to reorder documents and maximize LLM context window performance. Implements Hybrid Retrieval with Reciprocal Rank Fusion (RRF) and rigorous BEIR evaluation (NDCG, MAP, Recall, Precision).dspy-opt
PublicAdvanced RAG pipeline optimization framework using DSPy. Implements modular RAG pipelines with Query-Rewriting, Sub-Query Decomposition, and Hybrid Search via Weaviate. Automates prompt tuning and few-shot selection using MIPRO, COPRO, and BootstrapFewShot optimizers on datasets like FreshQA, HotpotQA, TriviaQA, Wikipedia and PubMedQA.biothink
Publicmed-reason-evals
Publicllm-finetuning
Publicavnlp.github.io
Publicgrpo
Publicprp
PublicPairwise Ranking Prompting (PRP): Zero-shot LLM reranking library implementing efficient pairwise strategies (Heapsort, Sliding Window, All-Pairs). Mitigates position bias via bidirectional comparison and ensures reliability with structured Pydantic validation. Built for Haystack pipelines.MedRAG
PublicscGPT
PublicBioReason
Publicdataloaders
Publichyperparameter-tuning
PublicEffect of Optimizer Selection and Hyperparameter Tuning on Training Efficiency and LLM Performancevectordb
PublicPipelines for Semantic Search, Metadata Filtering, Hybrid Search, Reranking, and Retrieval-Augmented Generation (RAG) on the TriviaQA, ARC, PopQA, FactScore, and Edgar datasets. These pipelines have been implemented using the Pinecone, Weaviate, Milvus, Qdrant and Chroma vector databases..github
PublicPPO-for-Beginners
PublicA simple and well styled PPO implementation. Based on my Medium series: https://medium.com/@eyyu/coding-ppo-from-scratch-with-pytorch-part-1-4-613dfc1b14c8.self-biorag
PublicGenePT
Publicfinbert-hf
Public