Pinned Loading
-
-
-
LLM-FineTuning-QLora
LLM-FineTuning-QLora PublicQLoRA fine-tuning of the Turkish Kumru-2B model on medical exam data using Unsloth.
Python 1
-
MLOps_process
MLOps_process PublicEnd-to-end customer churn MLOps pipeline with MLflow, FastAPI, Docker, pytest, and model experiment tracking.
Python
-
role-based-llm
role-based-llm PublicRole-based LLM assistant where the LLM is never the security boundary: three enforcement layers (tool visibility, Casbin re-check, per-level Postgres users), a leakage matrix with 0 leaks in 80 liv…
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.
