Sandy4321's repositories
agent_dingo
A microframework for creating simple AI agents.
aim
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
alibi-detect
Algorithms for outlier, adversarial and drift detection
amazon-sagemaker-llama2-response-streaming-recipes
Amazon SageMaker Llama 2 Inference via Response Streaming
aws-ai-intelligent-document-processing
Intelligent Document Processing with AWS AI Services and generative AI
backtracking_gpt
A non-RAG self-correcting GPT
CRAG
Corrective Retrieval Augmented Generation
data-fusion2024-geo
Open solution for geo task from Data Fusion Contest 2024
dfc2024_task2
Data Fusion Contest 2024 - Задача 2 «Отток». Публичное решение.
djl-serving
A universal scalable machine learning model deployment solution
foundation-model-benchmarking-tool
Foundation model benchmarking tool. Run any model on Amazon SageMaker and benchmark for performance across instance type and serving stack options.
Function-Calling-Mistral-7B
Function Calling Mistral 7B. Learn how to make functions call for open source LLMs.
generative-ai-demo-using-amazon-sagemaker-jumpstart-kr
This project shows the demos about how to generate stable diffusion images using AWS SageMaker Jumpstat.
huggingface-azure-acr-embedding
Repository for hosting Embedding Service Code
llm-chatbot-neo4j-langchain
This GitHub repo guides on building a RAG chatbot with LangChain & LLMs. It covers using LangChain, integrating Neo4j for data retrieval, and deploying with FastAPI & Streamlit. Ideal for AI engineers aiming to create advanced, data-informed chatbots.
llm-course-mlabonne
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Medical-RAG-using-Bio-Mistral-7B
This is a RAG implementation using Open Source stack. BioMistral 7B has been used to build this app along with PubMedBert as an embedding model, Qdrant as a self hosted Vector DB, and Langchain & Llama CPP as an orchestration frameworks.
Neo4js_RAG
Rag pipeline with Neo4js Knowledge Graph, Llama Index, and Zephyr7b
strictjson
A Strict JSON Framework for LLM Outputs
synthea_Synthetic-Patient-Population-Simulator
Synthetic Patient Population Simulator
VectorHub
VectorHub is a free, open-source learning website for people (software developers to senior ML architects) interested in adding vector retrieval to their ML stack.
ZSCL
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models