Skip to content

Instantly share code, notes, and snippets.

View MasanoriYamada's full-sized avatar

Masanori Yamada MasanoriYamada

  • Tokyo, Japan
View GitHub Profile
@MasanoriYamada
MasanoriYamada / agent loop
Created March 10, 2025 13:21 — forked from jlia0/agent loop
Manus tools and prompts
You are Manus, an AI agent created by the Manus team.
You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet
@MasanoriYamada
MasanoriYamada / r1.py
Created February 6, 2025 08:17 — forked from vgel/r1.py
script to run deepseek-r1 with a min-thinking-tokens parameter, replacing </think> with a random continuation string to extend the model's chain of thought
import argparse
import random
import sys
from transformers import AutoModelForCausalLM, AutoTokenizer, DynamicCache
import torch
parser = argparse.ArgumentParser()
parser.add_argument("question", type=str)
parser.add_argument(
@MasanoriYamada
MasanoriYamada / linear_sum_assignment_pytorch.py
Created August 2, 2023 03:30
linear_sum_assignment in pytorch
import torch
import random
from scipy.optimize import linear_sum_assignment as linear_sum_assignment_scipy
import time
def augmenting_path(cost, u, v, path, row4col, i):
device = cost.device
@MasanoriYamada
MasanoriYamada / lr_scheduler.ipynb
Last active May 6, 2023 16:50
torchopt lr scheduler
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@MasanoriYamada
MasanoriYamada / torch_jacobian.py
Created December 27, 2019 16:26 — forked from sbarratt/torch_jacobian.py
Get the jacobian of a vector-valued function that takes batch inputs, in pytorch.
def get_jacobian(net, x, noutputs):
x = x.squeeze()
n = x.size()[0]
x = x.repeat(noutputs, 1)
x.requires_grad_(True)
y = net(x)
y.backward(torch.eye(noutputs))
return x.grad.data
from __future__ import print_function
import threading
from joblib import Parallel, delayed
import Queue
import os
# Fix print
_print = print
_rlock = threading.RLock()
def print(*args, **kwargs):
@MasanoriYamada
MasanoriYamada / pg-pong.py
Created July 2, 2016 15:52 — forked from karpathy/pg-pong.py
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym
# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward
# Description:
# Joke commands.
#
# Commands:
# ぬるぽ - You reply with, "ガッ" When you post a "ぬるぽ" word.
#
# Notes:
# ネタ/ジョーク系のbot全般
module.exports = (robot) ->