fixing pipeline script

Signed-off-by: Jacob Renn <77127228+jacobrenn@users.noreply.github.com>

instruct_pipeline.py

@@ -108,59 +108,53 @@ class InstructionTextGenerationPipeline(Pipeline):
         return {"generated_sequence": generated_sequence, "input_ids": input_ids, "instruction_text": instruction_text}
 
     def postprocess(self, model_outputs, response_key_token_id, end_key_token_id, return_instruction_text):
-        generated_sequence = model_outputs["generated_sequence"][0]
+        sequence = model_outputs["generated_sequence"]
         instruction_text = model_outputs["instruction_text"]
 
-        generated_sequence = generated_sequence.numpy().tolist()
-        records = []
-        for sequence in generated_sequence:
-
-            # The response will be set to this variable if we can identify it.
-            decoded = None
-
-            # If we have token IDs for the response and end, then we can find the tokens and only decode between them.
-            if response_key_token_id and end_key_token_id:
-                # Find where "### Response:" is first found in the generated tokens.  Considering this is part of the
-                # prompt, we should definitely find it.  We will return the tokens found after this token.
-                response_pos = None
-                response_positions = np.where(sequence == response_key_token_id)[0]
-                if len(response_positions) == 0:
-                    pass
-                else:
-                    response_pos = response_positions[0]
-
-                if response_pos:
-                    # Next find where "### End" is located.  The model has been trained to end its responses with this
-                    # sequence (or actually, the token ID it maps to, since it is a special token).  We may not find
-                    # this token, as the response could be truncated.  If we don't find it then just return everything
-                    # to the end.  Note that even though we set eos_token_id, we still see the this token at the end.
-                    end_pos = None
-                    end_positions = np.where(sequence == end_key_token_id)[0]
-                    if len(end_positions) > 0:
-                        end_pos = end_positions[0]
-
-                    decoded = self.tokenizer.decode(sequence[response_pos + 1 : end_pos]).strip()
-            else:
-                # Otherwise we'll decode everything and use a regex to find the response and end.
-
-                fully_decoded = self.tokenizer.decode(sequence)
-
-                # The response appears after "### Response:".  The model has been trained to append "### End" at the
-                # end.
-                m = re.search(r"#+\s*Response:\s*(.+?)#+\s*End", fully_decoded, flags=re.DOTALL)
+        # The response will be set to this variable if we can identify it.
+        decoded = None
 
+        # If we have token IDs for the response and end, then we can find the tokens and only decode between them.
+        if response_key_token_id and end_key_token_id:
+            # Find where "### Response:" is first found in the generated tokens.  Considering this is part of the
+            # prompt, we should definitely find it.  We will return the tokens found after this token.
+            response_pos = None
+            response_positions = np.where(sequence == response_key_token_id)[0]
+            if len(response_positions) == 0:
+                pass
+            else:
+                response_pos = response_positions[0]
+
+            if response_pos:
+                # Next find where "### End" is located.  The model has been trained to end its responses with this
+                # sequence (or actually, the token ID it maps to, since it is a special token).  We may not find
+                # this token, as the response could be truncated.  If we don't find it then just return everything
+                # to the end.  Note that even though we set eos_token_id, we still see the this token at the end.
+                end_pos = None
+                end_positions = np.where(sequence == end_key_token_id)[0]
+                if len(end_positions) > 0:
+                    end_pos = end_positions[0]
+
+                decoded = self.tokenizer.decode(sequence[response_pos + 1 : end_pos]).strip()
+        else:
+            # Otherwise we'll decode everything and use a regex to find the response and end.
+
+            fully_decoded = self.tokenizer.decode(sequence)
+
+            # The response appears after "### Response:".  The model has been trained to append "### End" at the
+            # end.
+            m = re.search(r"#+\s*Response:\s*(.+?)#+\s*End", fully_decoded, flags=re.DOTALL)
+
+            if m:
+                decoded = m.group(1).strip()
+            else:
+                # The model might not generate the "### End" sequence before reaching the max tokens.  In this case,
+                # return everything after "### Response:".
+                m = re.search(r"#+\s*Response:\s*(.+)", fully_decoded, flags=re.DOTALL)
                 if m:
                     decoded = m.group(1).strip()
-                else:
-                    # The model might not generate the "### End" sequence before reaching the max tokens.  In this case,
-                    # return everything after "### Response:".
-                    m = re.search(r"#+\s*Response:\s*(.+)", fully_decoded, flags=re.DOTALL)
-                    if m:
-                        decoded = m.group(1).strip()
-
-            if return_instruction_text:
-                records.append({"instruction_text": instruction_text, "generated_text": decoded})
-            else:
-                records.append({'generated_text': decoded})
 
-        return records
+        if return_instruction_text:
+            return {"instruction_text": instruction_text, "generated_text": decoded}
+
+        return {'generated_text': decoded}