RuntimeError: shape '[3072, 2048]' is invalid for input of size 26214400错误

[gitelecman]

运行ktransformers出现以下错误输出

Traceback (most recent call last):
File "/home/xxxx/anaconda3/envs/ktransformers/bin/ktransformers", line 8, in
sys.exit(main())
^^^^^^
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/server/main.py", line 115, in main
create_interface(config=cfg, default_args=cfg)
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/server/utils/create_interface.py", line 27, in create_interface
GlobalInterface.interface = BackendInterface(default_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/server/backend/interfaces/ktransformers.py", line 50, in init
optimize_and_load_gguf(self.model, optimize_rule_path, gguf_path, config)
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/optimize/optimize.py", line 129, in optimize_and_load_gguf
load_weights(module, gguf_loader)
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/util/utils.py", line 86, in load_weights
load_weights(child, gguf_loader, prefix+name+".")
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/util/utils.py", line 88, in load_weights
module.load()
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/operators/base_operator.py", line 63, in load
utils.load_weights(child, self.gguf_loader, self.key+".")
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/util/utils.py", line 86, in load_weights
load_weights(child, gguf_loader, prefix+name+".")
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/util/utils.py", line 86, in load_weights
load_weights(child, gguf_loader, prefix+name+".")
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/util/utils.py", line 86, in load_weights
load_weights(child, gguf_loader, prefix+name+".")
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/util/utils.py", line 88, in load_weights
module.load()
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/operators/base_operator.py", line 63, in load
utils.load_weights(child, self.gguf_loader, self.key+".")
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/util/utils.py", line 86, in load_weights
load_weights(child, gguf_loader, prefix+name+".")
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/util/utils.py", line 88, in load_weights
module.load()
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/operators/linear.py", line 432, in load
self.generate_linear.load(w=w)
File "/home/xxxx/anaconda3/envs/ktransformers/lib/python3.11/site-packages/ktransformers/operators/linear.py", line 206, in load
weight = w[0].view(self.out_features, self.in_features).T
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: shape '[3072, 2048]' is invalid for input of size 26214400

请问原因是什么？

[gaoguangjun]

我也遇到了这个问题