qpwo

#!/usr/bin/env python3
import torch, gymnasium as gym, numpy as np, time, sys, threading, os, random
import torch.multiprocessing as mp
from torch import Tensor

from bg_record import log_step, bind_logger, log_close

# torch.set_num_threads(1)

NUM_PROCS = 16

NohTow

from datasets import load_dataset
from sentence_transformers import (
    SentenceTransformerTrainer,
    SentenceTransformerTrainingArguments,
)

from pylate import losses, models, utils

def main():
    # As ReasonIR do not re-upload the BRIGHT data, we need to load it from the original source

VictorTaelin

CHALLENGE

Develop an AI prompt that solves random 12-token instances of the A::B problem (defined here), with 90%+ success rate.

RULES

1. The AI will be given a <problem/> to solve.

We'll use your prompt as the SYSTEM PROMPT, and a specific instance of problem as the PROMPT, inside XML tags. Example:

alexgleith

hyperupcall

// I'm tired of extensions that automatically:
// - show welcome pages / walkthroughs
// - show release notes
// - send telemetry
// - recommend things
//
// This disables all of that stuff.
// If you have more config, leave a comment so I can add it!!

{

francois-rozet

#!/usr/bin/env python

import math
import matplotlib.pyplot as plt
import torch
import torch.nn as nn

from sklearn.datasets import make_moons
from torch import Tensor
from tqdm import tqdm

mayrajeo

noskill

import torch
import numpy
np = numpy
from geomloss import SamplesLoss  # See also ImagesLoss, VolumesLoss


# preferences, need to be converted to costs
# row i = cost of moving each item from c to place i
# making cost non-negative will not changes solution matrix P
preference = numpy.asarray([[2, 2, 1 , 0 ,0],

thomasbrandon

bfarzin