Pinned Repositories
biothink
Self-Reflective Question Answering for Biomedical Reasoning
dataloaders
Dataloaders is a versatile library designed for processing and formatting datasets to support various Retrieval-Augmented Generation (RAG) pipelines, facilitating efficient evaluation and analysis.
grpo
Group Relative Policy Optimization (GRPO) Implementations
hyperparameter-tuning
Effect of Optimizer Selection and Hyperparameter Tuning on Training Efficiency and LLM Performance
llm-blender
Ensembling LLMs using LLM-Blender
llm-finetuning
Pipelines for Fine-Tuning LLMs using SFT and RLHF
rag-model-training
Training LLMs for Retrieval Augmented Generation
rag-pipelines
Advanced RAG Pipelines and Evaluation: Self-Reflective RAG, Corrective RAG, Adaptive RAG, Sub-Query Generation and Routing, DSPy, DeepEval
rrf
Performance Evaluation of Rankers and RRF Techniques for Retrieval Pipelines
vectordb
Pipelines 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.
AVNLP's Repositories
avnlp/llm-blender
Ensembling LLMs using LLM-Blender
avnlp/rag-pipelines
Advanced RAG Pipelines and Evaluation: Self-Reflective RAG, Corrective RAG, Adaptive RAG, Sub-Query Generation and Routing, DSPy, DeepEval
avnlp/llm-finetuning
Pipelines for Fine-Tuning LLMs using SFT and RLHF
avnlp/rrf
Performance Evaluation of Rankers and RRF Techniques for Retrieval Pipelines
avnlp/dataloaders
Dataloaders is a versatile library designed for processing and formatting datasets to support various Retrieval-Augmented Generation (RAG) pipelines, facilitating efficient evaluation and analysis.
avnlp/dspy-opt
Advanced RAG Pipelines optimized with DSPy
avnlp/hyperparameter-tuning
Effect of Optimizer Selection and Hyperparameter Tuning on Training Efficiency and LLM Performance
avnlp/rankers
LLM based Pairwise, Setwise, and Listwise rankers.
avnlp/vectordb
Pipelines 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.
avnlp/biothink
Self-Reflective Question Answering for Biomedical Reasoning
avnlp/grpo
Group Relative Policy Optimization (GRPO) Implementations
avnlp/prp
Pairwise Ranking Prompting (PRP)
avnlp/rag-model-training
Training LLMs for Retrieval Augmented Generation
avnlp/.github
avnlp/finbert-hf
avnlp/avnlp.github.io
avnlp/BioReason
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
avnlp/direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)
avnlp/GenePT
avnlp/MedRAG
avnlp/PPO-for-Beginners
A 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.
avnlp/scGPT
avnlp/self-biorag
[ISMB '24] Self-BioRAG: Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models