Skip to content
View Bender1011001's full-sized avatar

Block or report Bender1011001

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. Markdown is supported. 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

Popular repositories Loading

  1. quadzilla-adrenaline-reversed quadzilla-adrenaline-reversed Public

    Complete reverse engineering of the Quadzilla Adrenaline diesel tuner — firmware decryption, BLE protocol, 117 parameters, decompiled code. Done entirely by AI.

    C 3

  2. GeoAnomalyMapper GeoAnomalyMapper Public

    Ground-deformation intelligence + landscape archaeology from free satellite data: validated InSAR sinkhole/subsidence detection (NASA OPERA/HyP3), and a Python reader for the open CORONA archive (1…

    Python 1

  3. ppo-vram-halver ppo-vram-halver Public

    Single-model dual-pass PPO/RLHF: toggle LoRA adapters on one model shell to drop the frozen reference-model VRAM copy. Benchmarked ~49% peak PPO-step memory reduction on a 3B model on an 8GB RTX 40…

    Python 1

  4. symmetric-bipolar-attention symmetric-bipolar-attention Public

    Signed attention for transformers — sinh/cosh attention giving weights in [-1,1] instead of softmax's positive-only, made FlashAttention/SDPA-compatible by channel doubling. Includes a from-scratch…

    Python 1

  5. FBA-Bench FBA-Bench Public

    Tick-based e-commerce AI benchmark — GAAP accounting, adversarial red-teaming, multi-agent competition across 180–365 decision steps. Live leaderboard at fbabench.com

    Python

  6. cascades-continual-peft-llm cascades-continual-peft-llm Public

    Continual PEFT for abliterated LLMs under 8GB via Stiefel-manifold-constrained updates. Best observed run: 35.91% reasoning accuracy, -1.46% BWT on a single RTX 4060 Ti (results vary widely across …

    Python