wassname

curseDownloader

0 0 0

Curse Modpack downloader

Updated 2026-07-27 11:02:08 +08:00

fbmtimelinecleaner

0 0 0

Facebook Mobile Timeline Cleaner. This is

Updated 2026-07-27 00:26:47 +08:00

openrouter_wrapper

0 0 0

Updated 2026-07-27 00:24:12 +08:00

adapters_as_hypotheses

Markdown 0 0 0

Each lora type adapter can tell us something about how to look at transformer internals, and they some with causal evidence

Updated 2026-07-19 11:39:41 +08:00

moral-maps

Python 0 0 0

tiny moral foundations vignettes. logprob eval for steering

Updated 2026-07-19 09:17:23 +08:00

soul-ab-test-scope-test

Python 0 0 0

Updated 2026-07-18 10:03:49 +08:00

openrouter-python-sdk-retry-errors

Python 0 0 0

Updated 2026-07-15 06:26:08 +08:00

jsteer

Jupyter Notebook 0 0 0

Updated 2026-07-14 13:55:25 +08:00

anz-2040-draft

HTML 0 0 0

ANZ 2040: the decisions Australia and New Zealand still get to make (draft proposal, retelling AI-2040 / Plan A from a middle-power view)

Updated 2026-07-12 09:20:28 +08:00

steer-heal-love

Python 0 0 0

Hypothesis: you can distill a steering vector into LoRA weights and "heal" the incoherency the vector injects by regularising the training (KL to base, or weight decay). Then loop and see what multiple rounds give you.

Updated 2026-06-30 15:37:34 +08:00

awesome-moral-evals

0 0 0

Curated list of datasets for evaluating moral/ethical behaviour of LLMs: dilemmas, norms, moral foundations, ethics, honesty, personas

Updated 2026-06-30 08:22:29 +08:00

lora-lite

Python 0 0 0

A hackable, single-file-per-variant LoRA library built on PyTorch forward hooks.

Updated 2026-06-19 08:47:41 +08:00

evil_MoE

Python 0 0 0

Putting the E in MoE with an evil expert (can initial seeding, cause follow up unwated behaviour to absorb into a MoE)

Updated 2026-06-14 13:06:38 +08:00

copilot-gpt4-service

0 0 0

Convert Github Copilot to ChatGPT

Updated 2026-06-13 13:55:35 +08:00

grpo_proj2

Python 0 0 0

Updated 2026-06-01 14:30:20 +08:00