diff --git a/results/sp30k_biqrnn_bs70 b/results/sp30k_biqrnn_bs70
new file mode 100644
index 0000000..5c658fd
--- /dev/null
+++ b/results/sp30k_biqrnn_bs70
@@ -0,0 +1,13 @@
+Starting from random weights                                                                                                                                             
+epoch  train_loss  valid_loss  accuracy_fwd  accuracy_bwd                                                                                                                
+1      3.669261    3.641705    0.399714      0.380689                                                                                                                    
+2      3.574335    3.547273    0.404729      0.385104                                                                                                                    
+3      3.573150    3.549644    0.403350      0.384167                                                                                                                    
+4      3.518714    3.499090    0.408166      0.389015
+5      3.477355    3.441828    0.413880      0.394777
+6      3.408005    3.366269    0.422041      0.402934
+7      3.314280    3.284519    0.431068      0.411727
+8      3.244735    3.205757    0.440180      0.421078
+9      3.170936    3.152495    0.446947      0.428045
+10     3.131996    3.138446    0.448782      0.430013
+Saving optimiser state at data/wiki/wikitext-103/models/sp30k/biqrnn_bs70.m
\ No newline at end of file
diff --git a/tests/test_end_to_end.py b/tests/test_end_to_end.py
index c3be22f..787c5a3 100644
--- a/tests/test_end_to_end.py
+++ b/tests/test_end_to_end.py
@@ -102,6 +102,25 @@ def test_ulmfit_fastai_bidir_end_to_end():
     )
     exp.train_lm(num_epochs=1)
 
+def test_ulmfit_moses_fa_bidir_end_to_end():
+    """ Test ulmfit with sentencepiece tokenizer on small wikipedia dataset.
+    """
+    imdb, wt2 = get_test_data()
+    lm_name = 'end-to-end-test-fastai'
+    cuda_id = 0
+    exp = ulmfit.pretrain_lm.LMHyperParams(
+        dataset_path=wt2,
+        lang='en',
+        cuda_id=cuda_id,
+        qrnn=True,
+        bidir=True,
+        tokenizer='vf',
+        max_vocab=100,
+        bs=2,
+        name=lm_name,
+    )
+    exp.train_lm(num_epochs=1)
+
 def test_ulmfit_sentencepiece_end_to_end():
     """ Test ulmfit with sentencepiece tokenizer on small wikipedia dataset.
     """
diff --git a/ulmfit/pretrain_lm.py b/ulmfit/pretrain_lm.py
index dd8142d..6169edf 100644
--- a/ulmfit/pretrain_lm.py
+++ b/ulmfit/pretrain_lm.py
@@ -44,6 +44,7 @@ import fastai_contrib.data as contrib_data
 class Tokenizers(Enum):
     SUBWORD='sb'
     MOSES='v'
+    MOSES_FA='vf'
     FASTAI='f'
 
 # tokenizers ={
@@ -182,8 +183,6 @@ class LMHyperParams:
             sp = get_sentencepiece(self.dataset_path, trn_path, self.name, vocab_size=self.max_vocab)
 
             data_lm = TextLMDataBunch.from_csv(self.dataset_path, 'train.csv', **sp, bs=self.bs, bptt=self.bptt, lm_type=self.lm_type)
-            itos = data_lm.train_ds.vocab.itos
-            stoi = data_lm.train_ds.vocab.stoi
         elif self.tokenizer is Tokenizers.MOSES:
             # read the already whitespace separated data without any preprocessing
             trn_tok = read_whitespace_file(trn_path)
@@ -209,12 +208,22 @@ class LMHyperParams:
             trn_ids = np.array([([stoi.get(w, stoi[UNK]) for w in s]) for s in trn_tok])
             val_ids = np.array([([stoi.get(w, stoi[UNK]) for w in s]) for s in val_tok])
 
-
-
             # data_lm = TextLMDataBunch.from_ids(dir_path, trn_ids, [], val_ids, [], len(itos))
             data_lm = TextLMDataBunch.from_ids(path=self.dataset_path, vocab=vocab, train_ids=trn_ids,
                                                valid_ids=val_ids, bs=self.bs, bptt=self.bptt,
                                                lm_type=self.lm_type)
+        elif self.tokenizer is Tokenizers.MOSES_FA:
+            try:
+                data_lm = TextLMDataBunch.load(self.cache_dir, '.', lm_type=self.lm_type)
+                print("Tokenized data loaded")
+            except FileNotFoundError:
+                print("Running tokenization")
+
+                pretokenized = Tokenizer(tok_func=BaseTokenizer, lang='en', pre_rules=None, post_rules=None)
+                data_lm = TextLMDataBunch.from_df(path=self.cache_dir, train_df=read_file(trn_path),
+                                                  valid_df=read_file(val_path), tokenizer=pretokenized,
+                                                  test_df=read_file(tst_path), classes=None, lm_type=self.lm_type)
+                data_lm.save('.')
         elif self.tokenizer is Tokenizers.FASTAI:
             try:
                 data_lm = TextLMDataBunch.load(self.cache_dir, '.', lm_type=self.lm_type)