Skip to content
View ALEX8642's full-sized avatar
  • 03:02 (UTC -05:00)

Block or report ALEX8642

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ALEX8642/README.md

Alexander Feht

Quality engineer (ASQ-CQE, 15+ years in regulated hardware manufacturing) who deploys and operates private LLM infrastructure: multi-node serving, evaluation gates, silent-failure monitoring and disaster recovery, run with the same discipline as a production line.

I build with AI coding agents (Claude Code, Codex, GitHub Copilot CLI). I set the architecture, constraints and acceptance criteria, then review, test, deploy and operate what they write.

On-prem LLM deployment & evaluation

Repo What it shows
LLM-chatbot Question answering over technical manuals in which every claim carries a verbatim quote, checked and highlighted on its source page: PaddleOCR-VL parsing with page coordinates, tables as data, hybrid retrieval with a Qwen3 reranker, any OpenAI-compatible model. A pre-registered held-out test with blind human grading: 80% of answers correct and supported against 42% for v1 (the pipeline and a larger model together). Try it in the browser: https://alex8642.github.io/LLM-chatbot/
onprem-llm-stack Two NVIDIA GB10 nodes serving large quantized models (MiniMax M2.7, Qwen3.5-122B, Qwen3.8-Flash-Next) tensor-parallel on vLLM / SGLang / Atlas, behind a LiteLLM gateway and OpenWebUI with SSO. Includes an A/B evaluation harness that caught a faster recipe failing long-context retrieval, a watchdog for a silent NaN-logits fault (detect → contain → correct → escalate), an Ansible rebuild with a written DR runbook, a measured trial of Cohere Command A+ (218B MoE, TP=2), and a tool-call eval of the Home Assistant voice agent
audio2report Dual-mic meeting recordings → deduplicated transcript → LLM audit report, fully local (WhisperX, pluggable local LLM backends, CPU/GPU Docker images, CI)
lights-out A self-hosted model that troubleshoots the network when the internet (and every cloud assistant) is down, tested on replayed incidents. It never gets a shell: read-only commands pass a policy enforced in code, and any fix is a closed list of scripts whose risk class decides whether it acts, asks me, or is refused. Scored on diagnosis, restraint and evidence, with success rates and 95% intervals per batch and energy per correct diagnosis measured at the wall plug. First batch: 0/5 correct at temperature 0 vs 4/5 at 0.7 on a two-cause DNS fault; no unsafe command proposed so far. Run as a reviewed-PR project: issues, ADRs, CI, changelog fragments
judge-msa A gauge study (Gage R&R) for LLM judges: repeatability, agreement between judges, bias against a human reference, and the smallest difference a judge can resolve, validated on simulated data with planted truth. Worked study on LLM-chatbot's judges with a protocol committed before the runs: identical verdicts at temperature 0, yet about 7% change when the key facts are reordered; each judge resolves differences only above 19–21 points; an unrecorded context-window default changed verdicts on long inputs

ML lifecycle on public data

Repo What it shows Headline
wafer-defect-classifier 9-class WM-811K wafer maps: focal loss + CBAM, temperature-scaled calibration, Grad-CAM++ macro-F1 0.92, ECE 0.003
wafer-ssl SimCLR pretraining on 638k unlabeled maps + 4-seed ensemble, with an ablation attributing the gain macro-F1 0.94
wafer-mixed Multi-label mixed-defect classification (MixedWM38), transfer study, cost-weighted per-label thresholds macro-F1 0.98
wafer-rootcause Simulated MES in DuckDB; SQL commonality analysis (z-tests + BH-FDR) recovers planted equipment faults precision@1 ~0.9–1.0
wafer-deploy FastAPI serving with a bit-for-bit parity test, three drift monitors, hysteresis retrain trigger, Prometheus + Grafana scored detection latency and false-alarm rate

Negative results stay in the docs. For example, a pseudo-labeling regression was rolled back and a loss-function bug is written up as a post-mortem.

Pinned Loading

  1. LLM-chatbot LLM-chatbot Public

    RAG - Question answering over technical manuals in which every claim carries a verbatim quote, checked and highlighted on its source page. Hybrid retrieval with a reranker, tables as data, any Open…

    Python 1

  2. onprem-llm-stack onprem-llm-stack Public

    Two-node NVIDIA GB10 LLM platform: tensor-parallel serving, LiteLLM gateway, SSO, evaluation harness, silent-fault watchdog, Ansible rebuild and DR

    Shell

  3. audio2report audio2report Public

    Dual-mic meeting recordings to deduplicated transcripts and LLM-generated audit reports, fully local (WhisperX + local LLM backends)

    Python

  4. wafer-deploy wafer-deploy Public

    FastAPI serving of a calibrated wafer-defect model with drift monitoring (MMD, PSI, ECE), hysteresis retrain trigger, Prometheus + Grafana

    Python

  5. wafer-defect-classifier wafer-defect-classifier Public

    ResNet-18 wafer defect classifier on WM-811K: focal loss, CBAM attention, temperature-scaled calibration, Grad-CAM++. Macro-F1 0.92

    Python

  6. wafer-rootcause wafer-rootcause Public

    Simulated-MES SQL root-cause pipeline: spatial defect signatures to tool/chamber attribution, scored against planted ground truth

    Python