Shekhar (Shake) Dewan ShakeDewan

⚙️

In Production

AI Expert

71 followers · 104 following

View GitHub Profile

Recently created

Least recently created

Recently updated

Least recently updated

ShakeDewan / grpo_demo.py

Created February 7, 2025 11:56 — forked from willccbb/grpo_demo.py

GRPO Llama-1B

	# train_grpo.py
	import re
	import torch
	from datasets import load_dataset, Dataset
	from transformers import AutoTokenizer, AutoModelForCausalLM
	from peft import LoraConfig
	from trl import GRPOConfig, GRPOTrainer

	# Load and prep dataset

ShakeDewan / contemplative-llms.txt

Created January 9, 2025 14:24 — forked from Maharshi-Pandya/contemplative-llms.txt

"Contemplative reasoning" response style for LLMs like Claude and GPT-4o

	You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

	## Core Principles

	1. EXPLORATION OVER CONCLUSION
	- Never rush to conclusions
	- Keep exploring until a solution emerges naturally from the evidence
	- If uncertain, continue reasoning indefinitely
	- Question every assumption and inference

ShakeDewan / spp_deep_network.py

Created January 23, 2020 03:53 — forked from yardstick17/spp_deep_network.py

Spatial pyramid pooling (SPP) is a pooling strategy to result in an output of fixed size. It will turn a 2D input of arbitrary size into an output of fixed dimension. Hence, the convolutional part of a DNN can be connected to a dense part with a fixed number of nodes even if the dimensions of the input image are unknown.

	CUSTOM_OUTPUT_CATEGORIES = 2
	import keras.backend as K
	from keras.engine.topology import Layer


	class SpatialPyramidPooling(Layer):
	'''Spatial pyramid pooling layer for 2D inputs.
	See Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition,
	K. He, X. Zhang, S. Ren, J. Sun
	# Arguments

ShakeDewan / keras_logistic_regression.py

Created July 4, 2019 16:02 — forked from fchollet/keras_logistic_regression.py

	from keras.models import Sequential
	from keras.layers import Dense

	x, y = ...
	x_val, y_val = ...

	# 1-dimensional MSE linear regression in Keras
	model = Sequential()
	model.add(Dense(1, input_dim=x.shape[1]))
	model.compile(optimizer='rmsprop', loss='mse')

ShakeDewan / hexgame.java

Created October 26, 2018 16:19 — forked from salamander2/hexgame.java

Hexagonal Grid in Java

	import java.awt.*;
	import javax.swing.*;
	import java.awt.event.*;

	/**********************************
	This is the main class of a Java program to play a game based on hexagonal tiles.
	The mechanism of handling hexes is in the file hexmech.java.

	Written by: M.H.
	Date: December 2012