zai-org

/

GLM-4.7-Flash

like 1.54k

Follow

Z.ai 9.7k

Loading safetensors checkpoint shards: 0% Completed | 0/48 [00:00<?, ?it/s]
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] WorkerProc failed to start.
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] Traceback (most recent call last):
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/v1/executor/multiproc_executor.py", line 720, in worker_main
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] worker = WorkerProc(*args, **kwargs)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/v1/executor/multiproc_executor.py", line 560, in init
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] self.worker.load_model()
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/v1/worker/gpu_worker.py", line 274, in load_model
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] self.model_runner.load_model(eep_scale_up=eep_scale_up)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/v1/worker/gpu_model_runner.py", line 3827, in load_model
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] self.model = model_loader.load_model(
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/model_loader/base_loader.py", line 58, in load_model
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] self.load_weights(model, model_config)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/model_loader/default_loader.py", line 288, in load_weights
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] loaded_weights = model.load_weights(self.get_all_weights(model_config, model))
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/transformers/base.py", line 492, in load_weights
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] return loader.load_weights(weights, mapper=self.hf_to_vllm_mapper)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/model_loader/online_quantization.py", line 173, in patched_model_load_weights
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] return original_load_weights(auto_weight_loader, weights, mapper=mapper)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 335, in load_weights
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] autoloaded_weights = set(self._load_module("", self.module, weights))
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 288, in _load_module
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] yield from self._load_module(
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 288, in _load_module
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] yield from self._load_module(
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 288, in _load_module
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] yield from self._load_module(
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] [Previous line repeated 2 more times]
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 319, in _load_module
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] raise ValueError(msg)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] ValueError: There is no module or parameter named 'model.layers.5.mlp.gate.e_score_correction_bias' in TransformersMoEForCausalLM