lucifertrj/news
Viewer • Updated • 33.5k • 20
🔄 In a Training Loop
Tarun Jain
lucifertrj
AI & ML interests
Deep Learning, FPGA, and ML
Recent Activity
posted an update 10 days ago
Automate Eval-Driven development using Coding Agents
Made a tutorial on what EDD is, how it works, and how you can use evaluations to improve your LLM-based application by analysing scores across experiments.
> building on Jeffrey's DeepEval article on EDD and Eugene Yan's product evals write up.
- Initial: The video walks through the initial setup of an RAG application used as the base for the experiments built using LangGraph and Qdrant.
- Step 1: A binary labelled dataset with critiques, versioned using OPIK.
- Step 2: Uses LLM-as-a-Judge OPIK evals to align the evaluator.
- Step 3: Runs the harness loop, which executes each experiment, scores it against the baseline, and uses tracing and experiment comparison to surface insights on what improved, what regressed, and where to tweak next.
... the Agent Skills and source code are open sourced on GitHub
> Complete Guide (source code link in description): https://www.youtube.com/watch?v=e6akw_fKWPk reacted to theirpost with 🔥 10 days ago
Published a guide to TurboQuant quantization: how the algorithm works and what Qdrant adds on top of it.
It also includes a benchmark comparing float32, scalar, binary and TurboQuant across BEIR's SciFact, ArguAna and NFCorpus, measured with recall@10, precision@10 and nDCG@10.
🔗 HF article: https://huggingface.co/blog/lucifertrj/turboquant-quantization-explained posted an update 12 days ago
Published a guide to TurboQuant quantization: how the algorithm works and what Qdrant adds on top of it.
It also includes a benchmark comparing float32, scalar, binary and TurboQuant across BEIR's SciFact, ArguAna and NFCorpus, measured with recall@10, precision@10 and nDCG@10.
🔗 HF article: https://huggingface.co/blog/lucifertrj/turboquant-quantization-explainedOrganizations
