santiviquez / ageml
Study the temporal performance degradation of machine learning models.
☆15Updated 11 months ago
Alternatives and similar repositories for ageml:
Users that are interested in ageml are comparing it to the libraries listed below
- An efficient, to-the-point, and easy-to-use checklist to following when deploying an ML model into production.☆31Updated last year
- Causal Impact but with MFLES and conformal prediction intervals☆34Updated 2 weeks ago
- ☆76Updated 7 months ago
- Framework for building and maintaining self-updating prompts for LLMs☆59Updated 7 months ago
- Very little code to make PyTorch Lightning models☆16Updated last year
- Repo for Hamel's Professional Website☆57Updated last week
- Drift detection module for machine learning pipelines.☆21Updated last year
- Retrieval Augmented Generation applications☆26Updated last year
- Table detection with Florence.☆12Updated 6 months ago
- ☆77Updated 7 months ago
- A framework for simulating e-commerce data and interactions that can be used to build recommendation systems☆10Updated last year
- Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by…☆29Updated 4 months ago
- Examples of using Evidently to evaluate, test and monitor ML models.☆18Updated 3 weeks ago
- Leverage your LangChain trace data for fine tuning☆40Updated 5 months ago
- Deployment examples for FastHTML☆33Updated 4 months ago
- Test LLMs automatically with Giskard and CI/CD☆29Updated 5 months ago
- ☆56Updated 2 months ago
- Quick Notebook Tutorials☆29Updated 2 months ago
- ☆49Updated 7 months ago
- Gzip and nearest neighbors for text classification☆56Updated last year
- Resources for exploring Generative Feedback Loops with Weaviate!☆36Updated this week
- Package designed for handling imbalanced classification☆18Updated last year
- Verbosity control for AI agents☆59Updated 7 months ago
- Demo on how to use Prefect with Docker☆25Updated 2 years ago
- Knowledge Graph Generator app☆30Updated 9 months ago
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absolute…☆48Updated 6 months ago
- Low latency, High Accuracy, Custom Query routers for Humans and Agents. Built by Prithivi Da☆90Updated 3 weeks ago
- ☆17Updated last month
- Use sync mode Playwright interactively, inside a Jupyter notebook☆14Updated last month
- Toolkit to forge scikit-learn compatible estimators☆18Updated 2 weeks ago