PrunaAI

/

InstructPLM-MPNN-ProGen2-xlarge-CATH42-QUANTO-int8bit-smashed

like 0

Follow

Pruna AI 116

• "transformers_modules.InstructPLM.MPNN-ProGen2-xlarge-CATH42.b1633e6969d66e87424421c64944416aac706d2b.modeling_InstructProGen.ProGenForCausalLM",
• "transformers_modules.InstructPLM.MPNN-ProGen2-xlarge-CATH42.b1633e6969d66e87424421c64944416aac706d2b.modeling_InstructProGen.ProGenModel",
• "torch.nn.modules.activation.MultiheadAttention",
• "transformers_modules.InstructPLM.MPNN-ProGen2-xlarge-CATH42.b1633e6969d66e87424421c64944416aac706d2b.structure.Resampler",
• "quanto.nn.qlinear.QLinear",
• "torch.FloatStorage",
• "transformers_modules.InstructPLM.MPNN-ProGen2-xlarge-CATH42.b1633e6969d66e87424421c64944416aac706d2b.modeling_InstructProGen.ProGenBlock",
• "torch.device",
• "torch.nn.modules.sparse.Embedding",
• "torch.HalfStorage",
• "transformers_modules.InstructPLM.MPNN-ProGen2-xlarge-CATH42.b1633e6969d66e87424421c64944416aac706d2b.modeling_InstructProGen.ProGenMLP",
• "torch.float16",
• "__builtin__.set",
• "torch.BoolStorage",
• "collections.OrderedDict",
• "transformers.generation.configuration_utils.GenerationConfig",
• "transformers.activations.NewGELUActivation",
• "transformers_modules.InstructPLM.MPNN-ProGen2-xlarge-CATH42.b1633e6969d66e87424421c64944416aac706d2b.structure.StructureTransformer",
• "quanto.tensor.qtype.qtype",
• "torch.nn.modules.dropout.Dropout",
• "transformers_modules.InstructPLM.MPNN-ProGen2-xlarge-CATH42.b1633e6969d66e87424421c64944416aac706d2b.configuration_progen.ProGenConfig",
• "torch._utils._rebuild_parameter",
• "transformers_modules.InstructPLM.MPNN-ProGen2-xlarge-CATH42.b1633e6969d66e87424421c64944416aac706d2b.modeling_InstructProGen.ProGenAttention",
• "torch._utils._rebuild_tensor_v2",
• "torch.nn.modules.container.ModuleList",
• "torch.nn.modules.normalization.LayerNorm",
• "torch.int8"

How to fix it?