Update README.md

README.md

@@ -96,7 +96,7 @@ out = model.generate(**inputs, output_scores=True, return_dict_in_generate=True,
 # sanity check that our sequences are expected length (1 + start token + end token = 3)
 for i, seq in enumerate(out.sequences):
     assert len(
-        seq) == 3, f"generated sequence {i} not of expected length, 3." \\
+        seq) == 3, f"generated sequence {i} not of expected length, 3." \\\\
                    f" Actual length: {len(seq)}"
 
 # get the scores for our only token of interest
@@ -108,8 +108,8 @@ scores = out.scores[0]
 # sanity check that these labels are always the top 3 scoring
 for i, sequence_scores in enumerate(scores):
     top_scores = sequence_scores.argsort()[-3:]
-    assert set(top_scores.tolist()) == set(label_inds), \\
-        f"top scoring tokens are not expected for this task." \\
+    assert set(top_scores.tolist()) == set(label_inds), \\\\
+        f"top scoring tokens are not expected for this task." \\\\
         f" Expected: {label_inds}. Got: {top_scores.tolist()}."
 
 # cut down scores to our task labels
@@ -135,7 +135,7 @@ print(entail_vs_contra_probas)
 
 # or we can show probas similar to `ZeroShotClassificationPipeline`
 # this gives a zero-shot classification style output across labels
-entail_scores = scores[:, 0]
+entail_scores = scores[:, entailment_ind]
 entail_probas = softmax(entail_scores, dim=0)
 print(entail_probas)
 # tensor([7.6341e-03, 4.2873e-04, 9.9194e-01])