Its error when i used in vllm
Here is the error message:
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 361, in from_engine_args
engine = cls(
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 319, in init
self.engine = self._init_engine(*args, **kwargs)
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 437, in _init_engine
return engine_class(*args, **kwargs)
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 148, in init
self.model_executor = executor_class(
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/executor/ray_gpu_executor.py", line 382, in init
super().init(*args, **kwargs)
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/executor/executor_base.py", line 41, in init
self._init_executor()
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/executor/ray_gpu_executor.py", line 45, in _init_executor
self._init_workers_ray(placement_group)
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/executor/ray_gpu_executor.py", line 182, in _init_workers_ray
self._run_workers(
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/executor/ray_gpu_executor.py", line 318, in _run_workers
driver_worker_output = self.driver_worker.execute_method(
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/worker/worker_base.py", line 158, in execute_method
raise e
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/worker/worker_base.py", line 149, in execute_method
return executor(*args, **kwargs)
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/worker/worker.py", line 117, in load_model
self.model_runner.load_model()
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/worker/model_runner.py", line 162, in load_model
self.model = get_model(
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/model_executor/model_loader/init.py", line 19, in get_model
return loader.load_model(model_config=model_config,
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/model_executor/model_loader/loader.py", line 224, in load_model
model.load_weights(
File "/media/llm/story_generation_manager/env/lib/python3.10/site-packages/vllm/model_executor/models/llama.py", line 411, in load_weights
param = params_dict[name]
KeyError: 'model.layers.0.mlp.down_proj.g_idx'