SagnikMukherjee/sparsity_in_rl
Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
This project helps machine learning researchers understand how reinforcement learning (RL) adapts large language models (LLMs). By analyzing changes between an instruction-tuned LLM and an RL-finetuned version, it shows which parts of the model learned new behaviors. Researchers can input two model checkpoints and identify the specific "subnetworks" that were modified by RL.
Use this if you are a machine learning researcher studying the efficiency and mechanisms of finetuning large language models with reinforcement learning.
Not ideal if you are looking for a tool to train or deploy large language models, or if you are not working with pre-trained and RL-finetuned model checkpoints.
Stars
12
Forks
4
Language
Python
License
—
Category
Last pushed
Oct 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/SagnikMukherjee/sparsity_in_rl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hud-evals/hud-python
OSS RL environment + evals toolkit
hiyouga/EasyR1
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
OpenRL-Lab/openrl
Unified Reinforcement Learning Framework
sail-sg/oat
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning,...
opendilab/awesome-RLHF
A curated list of reinforcement learning with human feedback resources (continually updated)