Mohd Kaif's repositories
RAG-with-KnowledgeGraph
RAG with Knowledge Graph
LLM-FineTuning-for-Sentiment-Classification
Fine-Tuning Microsoft Phi-2 for financial news sentiment analysis improved accuracy from 0.349 to 0.872 and reduced training loss by 38%. Dataset: 4846 entries with "Neutral," "Positive," and "Negative" labels.
Agri-Llama
Introducing an advanced RAG-based Question Answering System for Agriculture, seamlessly combining Llama-2 FAISS and Hugging Face's dataset for efficient and precise domain-specific responses.
Table2Text
Table2Text is a Streamlit app using the Mistral-8x7b-32k model and Langchain framework to handle queries on tabular data like CSVs and Pandas DataFrames.
AB-Testing
Awesome List of resources on Agile Software Development.
llm4IndicLanguage
Fine Tuning Open Source LLMs for Indic Language
SolarPanel-Tilt-Optimization
The SolarPanel-Tilt-Optimization project uses machine learning to optimize solar panel angles for maximum efficiency, analyzing solar and environmental data to provide actionable insights and performance metrics.
cookbook
Open-source AI cookbook
Crop-Recommendation
Smart Crop Selection: Machine Learning for Precise Recommendations in Diverse Environments
dspy
DSPy: The framework for programming—not prompting—foundation models
haystack
:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
HistoryQnA
Engineered a Document Based Question Answering System with Langchain, Pinecone and GPT-4
indicnlp_catalog
A collaborative catalog of NLP resources for Indic languages
langchain
⚡ Building applications with LLMs through composability ⚡
phoenix
AI Observability & Evaluation - Evaluate, troubleshoot, and fine tune your LLM, CV, and NLP models in a notebook.
sec-ai
A comprehensive open-source toolkit for AI-powered analysis and interpretation of SEC EDGAR filings, providing valuable insights for investors, fintech developers, and researchers.
sec-parser
Parse SEC EDGAR HTML documents into a tree of elements that correspond to the visual structure of the document.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.