Skip to content
View vrunm's full-sized avatar
7 followers · 16 following

Achievements

Achievement: Pair Extraordinairex2Achievement: StarstruckAchievement: Pull Sharkx3Achievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex2Achievement: StarstruckAchievement: Pull Sharkx3Achievement: Quickdraw

Organizations

@avnlp

Block or report vrunm

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
vrunm/README.md

Hi, I am Varun!

AI developer working in the enhancement and development of applications based on Large Language Models (LLMs).

Developing Open-Source software - AVNLP:

  • BioThink: Self-Reflective Question-Answering for Biomedical Reasoning.

  • LLM-Finetuning: Pipelines for Fine-Tuning LLMs using SFT and RLHF.

  • GRPO: Group Relative Policy Optimization (GRPO) Implementations.

  • 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, DeepEval.

  • DSPy-Opt: Advanced RAG Pipelines optimized with DSPy.

  • PRP: Implementation of Pairwise Ranking Prompting (PRP) technique.

  • Rankers: LLM based Pairwise, Setwise, and Listwise rankers.

  • RRF: Performance Evaluation of Rankers and RRF Techniques for Retrieval Pipelines.

  • LLM Blender: Ensembling LLMs using LLM-Blender.

  • Financial Dashboard : Built an end-to-end Financial Dashboard that collects and consolidates all of a business's critical observations in one place using the information obtained from the annual 10-K SEC Filings. The financial dashboard contains:

    • Insights and summaries for different sections from annual corporate filings.

    • Sentiment-based score that measures the company's performance over a certain time period.

    • Identification of Important topics and Frequently occuring words mentioned in the report.

Open Source Contributions:

Pinned Loading

  1. avnlp/biothink avnlp/biothink Public

    Self-Reflective Question Answering for Biomedical Reasoning

    Python 5 1

  2. avnlp/grpo avnlp/grpo Public

    Group Relative Policy Optimization (GRPO) Implementations

    Python 4

  3. avnlp/rag-model-training avnlp/rag-model-training Public

    Training 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 r…

    Python 6 2

  4. avnlp/llm-finetuning avnlp/llm-finetuning Public

    Pipelines for Fine-Tuning LLMs using SFT and RLHF

    Python 6 2

  5. avnlp/rag-pipelines avnlp/rag-pipelines Public

    Advanced RAG Pipelines and Evaluation

    Python 10 1

  6. avnlp/dspy-opt avnlp/dspy-opt Public

    Advanced 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 …

    Python 6 1