最新update的代码中，web_demo推理时报错

[feyxong]

报错定位在modeling_chatglm:
hello

/opt/conda/lib/python3.7/site-packages/transformers/tokenization_utils_base.py:717: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:230.)
tensor = as_tensor(value)
Traceback (most recent call last):
File "/opt/conda/lib/python3.7/site-packages/gradio/routes.py", line 400, in run_predict
event_data=event_data,
File "/opt/conda/lib/python3.7/site-packages/gradio/blocks.py", line 1109, in process_api
fn_index, inputs, iterator, request, event_id, event_data
File "/opt/conda/lib/python3.7/site-packages/gradio/blocks.py", line 930, in call_function
utils.async_iteration, iterator, limiter=self.limiter
File "/opt/conda/lib/python3.7/site-packages/anyio/to_thread.py", line 32, in run_sync
func, *args, cancellable=cancellable, limiter=limiter
File "/opt/conda/lib/python3.7/site-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "/opt/conda/lib/python3.7/site-packages/anyio/_backends/_asyncio.py", line 867, in run
result = context.run(func, *args)
File "/opt/conda/lib/python3.7/site-packages/gradio/utils.py", line 490, in async_iteration
return next(iterator)
File "web_demo_belle.py", line 38, in predict
temperature=temperature):
File "/opt/conda/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 43, in generator_context
response = gen.send(None)
File "/mnt/workspace/InstructGLM/modeling_chatglm.py", line 1153, in stream_chat
for outputs in self.stream_generate(**input_ids, **gen_kwargs):
File "/opt/conda/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 43, in generator_context
response = gen.send(None)
File "/mnt/workspace/InstructGLM/modeling_chatglm.py", line 1264, in stream_generate
outputs, model_kwargs, is_encoder_decoder=self.config.is_encoder_decoder
File "/opt/conda/lib/python3.7/site-packages/transformers/generation/utils.py", line 721, in _update_model_kwargs_for_generation
[attention_mask, attention_mask.new_ones((attention_mask.shape[0], 1))], dim=-1
RuntimeError: Tensors must have same number of dimensions: got 4 and 2

[zongking123]

+1

[yanqiangmiffy]

需要更新一下modeling_chatglm.py?

https://huggingface.co/THUDM/chatglm-6b/tree/main

这里有类似的问题：THUDM/ChatGLM-6B#374