Right, ok. I needed to set eval_batch_size=1. and I can keep hidden=model.init_hidden(1). That makes the dimensions agree.
The only issue is that “output” then ends up being [20x1x10000] instead of [1x1x10000] like the remainder of the code expects. So I grab only the last element of output via
output = output[-1]
The following, then, is some working code for generate.py that feeds it an initial sequence of length 20! Thanks for your help! 
###############################################################################
# Language Modeling on Penn Tree Bank
#
# This file generates new sentences sampled from the language model
#
###############################################################################
import argparse
import time
import math
import torch
import torch.nn as nn
from torch.autograd import Variable
import data
parser = argparse.ArgumentParser(description='PyTorch PTB Language Model')
# Model parameters.
parser.add_argument('--data', type=str, default='./data/penn',
help='location of the data corpus')
parser.add_argument('--checkpoint', type=str, default='./model.pt',
help='model checkpoint to use')
parser.add_argument('--outf', type=str, default='generated.txt',
help='output file for generated text')
parser.add_argument('--words', type=int, default='1000',
help='number of words to generate')
parser.add_argument('--seed', type=int, default=1111,
help='random seed')
parser.add_argument('--cuda', action='store_true',
help='use CUDA')
parser.add_argument('--temperature', type=float, default=1.0,
help='temperature - higher will increase diversity')
parser.add_argument('--log-interval', type=int, default=100,
help='reporting interval')
args = parser.parse_args()
# Set the random seed manually for reproducibility.
torch.manual_seed(args.seed)
if torch.cuda.is_available():
if not args.cuda:
print("WARNING: You have a CUDA device, so you should probably run with --cuda")
else:
torch.cuda.manual_seed(args.seed)
if args.temperature < 1e-3:
parser.error("--temperature has to be greater or equal 1e-3")
with open(args.checkpoint, 'rb') as f:
model = torch.load(f)
if args.cuda:
model.cuda()
else:
model.cpu()
def batchify(data, bsz): # breaks into parallel streams
nbatch = data.size(0) // bsz
data = data.narrow(0, 0, nbatch * bsz)
data = data.view(bsz, -1).t().contiguous()
if args.cuda:
data = data.cuda()
return data
corpus = data.Corpus(args.data)
ntokens = len(corpus.dictionary)
def batchify(data, bsz): # breaks into parallel streams
nbatch = data.size(0) // bsz
data = data.narrow(0, 0, nbatch * bsz)
data = data.view(bsz, -1).t().contiguous()
if args.cuda:
data = data.cuda()
return data
eval_batch_size = 1
test_data = batchify(corpus.test, eval_batch_size)
hidden = model.init_hidden(1)
def get_batch(source, i, evaluation=False):
bptt = 20
seq_len = min(bptt, len(source) - 1 - i)
data = Variable(source[i:i+seq_len], volatile=evaluation)
target = Variable(source[i+1:i+1+seq_len].view(-1))
return data, target
input, target = get_batch(test_data, 0, evaluation=True)
#input = Variable(torch.rand(1, 1).mul(ntokens).long(), volatile=True)
#print("input = ",input)
if args.cuda:
input.data = input.data.cuda()
with open(args.outf, 'w') as outf:
for i in range(args.words):
output, hidden = model(input, hidden)
output = output[-1]
# print("output = ",output)
word_weights = output.squeeze().data.div(args.temperature).exp().cpu()
word_idx = torch.multinomial(word_weights, 1)[0]
input.data.fill_(word_idx)
word = corpus.dictionary.idx2word[word_idx]
outf.write(word + ('\n' if i % 20 == 19 else ' '))
if i % args.log_interval == 0:
print('| Generated {}/{} words'.format(i, args.words))
print(" ")