PrunaAI

/

Writer-palmyra-base-QUANTO-float8bit-smashed

like 0

Follow

Pruna AI 272

• "torch.nn.modules.container.ModuleList",
• "transformers.models.gpt2.modeling_gpt2.GPT2LMHeadModel",
• "transformers.models.gpt2.modeling_gpt2.GPT2Model",
• "transformers.pytorch_utils.Conv1D",
• "quanto.tensor.qtype.qtype",
• "collections.OrderedDict",
• "transformers.activations.GELUActivation",
• "torch.bfloat16",
• "__builtin__.set",
• "transformers.models.gpt2.configuration_gpt2.GPT2Config",
• "torch._C._nn.gelu",
• "torch.device",
• "torch.nn.modules.sparse.Embedding",
• "transformers.models.gpt2.modeling_gpt2.GPT2MLP",
• "torch._utils._rebuild_parameter",
• "transformers.models.gpt2.modeling_gpt2.GPT2Block",
• "torch.FloatStorage",
• "torch.nn.modules.dropout.Dropout",
• "torch.nn.modules.normalization.LayerNorm",
• "torch.float8_e4m3fn",
• "torch.BoolStorage",
• "transformers.generation.configuration_utils.GenerationConfig",
• "transformers.models.gpt2.modeling_gpt2.GPT2SdpaAttention",
• "torch._utils._rebuild_tensor_v2",
• "quanto.nn.qlinear.QLinear",
• "torch.BFloat16Storage"

How to fix it?