Skip to content
View kok-o's full-sized avatar

Block or report kok-o

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
kok-o/README.md

Featured Projects

Deterministic context compiler and policy engine for AI coding assistants (Gemini, Claude Code, Cursor, Copilot, Aider, Zed).


Tech Stack

AI & Systems
Python PyTorch Docker Linux


Frontend & Web
TypeScript JavaScript React Next.js Tailwind CSS


Backend, Data & Tooling
Node.js PostgreSQL Prisma Supabase GitHub Actions Git


Open-Source Contributions

Open-source library for training, fine-tuning, and distillation of LLMs on PyTorch (26 author Pull Requests):

  • GPU/Host Async Optimization (PR #1026): Implemented DistillNonfiniteTracker to catch non-finite teacher logits on GPU tensors without device-to-host synchronization (.item()), preventing throughput stalls during distillation.
  • Unified Callback Architecture (PR #1023): Unified callback parameter extraction (soup_callback_kwargs) across all 16 trainers (sft, grpo, dpo, ppo, distill, etc.), adding schema gating and AST validation tests.
  • RLHF Reward Hacking Stress Tests (PR #918): Added structure-preserving adversarial attack families (wrapped_junk, answer_spray) to evaluate verifier robustness against reward gaming in reasoning models.
  • Cross-Platform Security & CI Gates (PR #1024, PR #921): Hardened Windows symlink and TOCTOU defense in draft registries and unified CLI exit code taxonomy (0/2/3) across evaluation gate commands.

Contribution Activity

github-snake

(⌐■_■)

Pinned Loading

  1. contextos-agents contextos-agents Public

    Deterministic context and policy compiler for supported AI coding agents.

    JavaScript 9 1

  2. MakazhanAlpamys/Soup MakazhanAlpamys/Soup Public

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

    Python 7.4k 1.2k