Added position_ids input

README.md

@@ -79,9 +79,11 @@ def generate_text(model_path, prompt, tokenizer, max_gen_tokens, total_sequence,
     inputs_dict = {}
     inputs_dict['input_ids'] = actual_input[:, :window].reshape(1, window).numpy()
     inputs_dict['attention_mask'] = first_attention
+    index_pos = sum(first_attention[0])
+    inputs_dict['position_ids'] = np.concatenate((np.zeros([1, total_sequence - index_pos], dtype = 'int64'), np.arange(index_pos, dtype = 'int64').reshape(1, index_pos)), axis=1)
     inputs_dict['tree_attention'] = np.triu(-65504*np.ones(total_sequence), k= 1).astype('float16').reshape(1, 1, total_sequence, total_sequence)
     for name in inputs_names:
-        if name == 'input_ids' or name == 'attention_mask' or name=='tree_attention': continue
+        if name == 'input_ids' or name == 'attention_mask' or name == 'position_ids' or name == 'tree_attention': continue
         inputs_dict[name] = np.zeros([1, n_heads, context-window, 256], dtype="float16")
     index = 0
     new_token = np.array([10])
@@ -113,6 +115,8 @@ def generate_text(model_path, prompt, tokenizer, max_gen_tokens, total_sequence,
                 inputs_dict['input_ids']= total_input[:, j:next_index].reshape(1, window)
             elif name == 'attention_mask':
                 inputs_dict['attention_mask'] = np.concatenate((np.zeros((1, total_sequence-next_index), dtype = 'int64'), np.ones((1, next_index), dtype = 'int64')), axis=1)
+            elif name == 'position_ids':
+                    inputs_dict['position_ids'] = np.concatenate((np.zeros([1, total_sequence - next_index], dtype = 'int64'), np.arange(next_index, dtype = 'int64').reshape(1, next_index)), axis=1)
             elif name == 'tree_attention': continue
             else:
                 old_name = name.replace("past_key_values", "present")

model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5ed76fc66299844bfe558c652a7a69eaa3eb4d602adeb3a290fe06bd5d94e7
-size 1165674
+oid sha256:79c9901be390f5887505a64c216e7a0346ef4246d24e5e60c795ae942530732c
+size 1164997

model_tree_in.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fcdd407a7acf2633bd9f4336f98f91ceeebf40c2cc8d49c3c0eb95c8da791784
-size 1172231