chatglm4用lora训练后，推理报错

[BigCakeLove]

Traceback (most recent call last):
File "/root/miniconda3/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/root/miniconda3/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/transformers/generation/utils.py", line 1914, in generate
result = self._sample(
File "/root/miniconda3/lib/python3.10/site-packages/transformers/generation/utils.py", line 2651, in _sample
outputs = self(
File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/CHATGLM4/modeling_chatglm.py", line 1005, in forward
transformer_outputs = self.transformer(
File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/CHATGLM4/modeling_chatglm.py", line 901, in forward
hidden_states, presents, all_hidden_states, all_self_attentions = self.encoder(
File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/CHATGLM4/modeling_chatglm.py", line 726, in forward
layer_ret = layer(
File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/CHATGLM4/modeling_chatglm.py", line 629, in forward
attention_output, kv_cache = self.self_attention(
File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/root/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/CHATGLM4/modeling_chatglm.py", line 494, in forward
cache_k, cache_v = kv_cache
ValueError: too many values to unpack (expected 2)

[hiyouga]

下载 transformers 4.41.2