tokestermw

# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer

tokestermw

import torch
import torch.nn as nn
import torch.nn.functional as F

# helpers

def make_unit_length(x, epsilon=1e-6):
    norm = x.norm(p=2, dim=-1, keepdim=True)
    return x.div(norm + epsilon)

tokestermw

tokestermw

Shortlink: goo.gl/wSuuS9

Supplementary Materials for Generating Wikipedia by Summarizing Long Sequences

The github repository will soon be available at github.com/tensorflow/tensor2tensor/tree/master/tensor2tensor/data_generators/wikisum

tokestermw

tokestermw

import random


class TicTacToe:
    def __init__(self, playerX, playerO):
        self.board = [' ']*9
        self.playerX, self.playerO = playerX, playerO
        self.playerX_turn = random.choice([True, False])

    def play_game(self):

tokestermw

Key-Value Memory Networks for Directly Reading Documents

Introduction

• Knowledge Bases (KBs) are effective tools for Question Answering (QA) but are often too restrictive (due to fixed schema) and too sparse (due to limitations of Information Extraction (IE) systems).
• The paper proposes Key-Value Memory Networks, a neural network architecture based on Memory Networks that can leverage both KBs and raw data for QA.
• The paper also introduces MOVIEQA, a new QA dataset that can be answered by a perfect KB, by Wikipedia pages and by an imperfect KB obtained using IE techniques thereby allowing a comparison between systems using any of the three sources.
• Link to the paper.

Related Work

tokestermw

""" 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

tokestermw

#!/usr/bin/env python
# coding: utf-8
"""Sampling Sequence Data from model"""

import numpy as np
import tensorflow as tf
import json
import cPickle as pickle
import itertools as it
from rnnlib import PTBModel

tokestermw

B = self.igor.batch_size
R = self.igor.rnn_size
S = self.igor.max_sequence_len
V = self.igor.vocab_size
E = self.igor.embedding_size
### loaded from glove
emb_W = self.igor.embeddings.astype(theano.config.floatX)

## dropout parameters
p_emb = self.igor.p_emb_dropout