agentic-learning-ai-lab/deleting-weights
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 6 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 5 days ago.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
Research code for Deletion Tuning, a post-training method that learns a binary mask over the gate projection of an LLM's transformer blocks, zeroing a small fraction of pretrained weights. It covers training with GRPO, SFT and on-policy self-distillation, saving masks as…
Who it's for
Researchers and ML engineers studying LLM post-training and continual learning who want to reproduce the paper's GRPO, SFT and SDFT experiments
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up agentic-learning-ai-lab/deleting-weights in my project. Follow its README: https://github.com/agentic-learning-ai-lab/deleting-weights. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/agentic-learning-ai-lab/deleting-weights?ref=badge)Similar repos
- datawhalechina/agentic-rl-lab
A collection of reproductions and tutorials of reinforcement learning algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, OPSD, Search-R1, ReTool and ALFWorld. Each method is explained and imp
- NVlabs/ASPIRE
A research framework for robotics in which an LLM-driven coding agent refines sensorimotor skills through iterative debugging and evolutionary search instead of gradient-based training. Evaluated on L
- drost-ai/tinker-ai-skill
An Agent Skill that guides a coding agent through a nine-step pipeline to turn Claude Code session transcripts into a supervised fine-tuning dataset, train a LoRA on Tinker, merge it, and convert it t
- togethercomputer/HybridAgent
Research code for HybridAgent, an LLM agent that alternates between latent reasoning and text-based actions in one generation. It maps last-layer hidden states back to input embeddings via HybridLink,
- DAGroup-PKU/ResearchBoost-Agent
An autonomous agent that profiles bottlenecks in AI training code, implements optimizations, and validates speedups against a frozen judge that checks bitwise equivalence and statistical training equi
- MUSE-AI-Lab/ReMCTS
Research code for ReMCTS, a Monte Carlo Tree Search method for LLM code generation. Each candidate program is executed in a subprocess, failures are stored as structured reflections in path and global