Merge branch 'main' of hf.co:Esperanto/llama3-8b-Instruct-kvc-fp16-onnx into main

README.md

@@ -79,8 +79,9 @@ 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
+    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': continue
+        if name == 'input_ids' or name == 'attention_mask' or name == 'tree_attention': continue
         inputs_dict[name] = np.zeros([1, n_heads, context-window, 128], dtype="float16")
     index = 0
     new_token = np.array([10])
@@ -112,6 +113,7 @@ 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 == 'tree_attention': continue
             else:
                 old_name = name.replace("past_key_values", "present")
                 inputs_dict[name] = outs_dictionary[old_name][:, :, next_index-old_j:context-window+(next_index - old_j), :]