touchwolf
commented
1 month ago I encountered the same issue. I resolved it by changing the "load chatglm3 model" node to "(download) load chatglm3 model" node, without changing the model save location. After this modification, everything worked fine.
Error occurred when executing LoadChatGLM3:
Only Tensors of floating point and complex dtype can require gradients
File "I:\AI\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "I:\AI\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "I:\AI\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "I:\AI\ComfyUI\custom_nodes\ComfyUI-KwaiKolorsWrapper\nodes.py", line 124, in loadmodel text_encoder.quantize(8) File "I:\AI\ComfyUI\custom_nodes\ComfyUI-KwaiKolorsWrapper\kolors\models\modeling_chatglm.py", line 852, in quantize quantize(self.encoder, weight_bit_width) File "I:\AI\ComfyUI\custom_nodes\ComfyUI-KwaiKolorsWrapper\kolors\models\quantization.py", line 155, in quantize layer.self_attention.query_key_value = QuantizedLinear( ^^^^^^^^^^^^^^^^ File "I:\AI\ComfyUI\custom_nodes\ComfyUI-KwaiKolorsWrapper\kolors\models\quantization.py", line 141, in init self.weight = Parameter(self.weight.to(device), requires_grad=False) ^^^^^^^^^^^ File "I:\AI\ComfyUI.ext\Lib\site-packages\torch\nn\modules\module.py", line 1726, in setattr self.register_parameter(name, value) File "I:\AI\ComfyUI.ext\Lib\site-packages\accelerate\big_modeling.py", line 123, in register_empty_parameter module._parameters[name] = param_cls(module._parameters[name].to(device), kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "I:\AI\ComfyUI.ext\Lib\site-packages\torch\nn\parameter.py", line 40, in new return torch.Tensor._make_subclass(cls, data, requires_grad)