Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.
K V Sandeep Moudgalya moudgalyakvs
moudgalyakvs
/ grpo_demo.py
Created
May 19, 2025 02:09
— forked from willccbb/grpo_demo.py
GRPO Llama-1B
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # train_grpo.py | |
| # | |
| # See https://github.com/willccbb/verifiers for ongoing developments | |
| # | |
| """ | |
| citation: | |
| @misc{brown2025grpodemo, | |
| title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models}, | |
| author={Brown, William}, |
moudgalyakvs
/ normcore-llm.md
Created
October 6, 2024 04:24
— forked from veekaybee/normcore-llm.md
Normcore LLM Reads