Skip to content

Instantly share code, notes, and snippets.

@willccbb
willccbb / grpo_demo.py
Last active October 25, 2025 16:39
GRPO Llama-1B
# 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},
@secemp9
secemp9 / mediapipe_landmark.py
Created September 30, 2024 02:31
fixed yacine code
import cv2
import numpy as np
import mediapipe as mp
# Initialize mediapipe Face Mesh and Hands solutions
mp_face_mesh = mp.solutions.face_mesh
mp_hands = mp.solutions.hands
mp_drawing = mp.solutions.drawing_utils
mp_drawing_styles = mp.solutions.drawing_styles