PrunaAI

/

vinai-PhoGPT-4B-Chat-QUANTO-int8bit-smashed

like 0

Follow

Pruna AI 112

• "transformers_modules.vinai.PhoGPT-4B-Chat.116013fa63f8c4025739487e1cbff65b7375bbe2.attention.scaled_multihead_dot_product_attention",
• "quanto.nn.qlinear.QLinear",
• "torch._utils._rebuild_parameter",
• "torch.bfloat16",
• "transformers_modules.vinai.PhoGPT-4B-Chat.116013fa63f8c4025739487e1cbff65b7375bbe2.modeling_mpt.MPTModel",
• "torch._C._nn.gelu",
• "transformers_modules.vinai.PhoGPT-4B-Chat.116013fa63f8c4025739487e1cbff65b7375bbe2.blocks.MPTBlock",
• "transformers.generation.configuration_utils.GenerationConfig",
• "torch.nn.modules.dropout.Dropout",
• "torch.BFloat16Storage",
• "__builtin__.set",
• "transformers_modules.vinai.PhoGPT-4B-Chat.116013fa63f8c4025739487e1cbff65b7375bbe2.attention.MultiheadAttention",
• "torch.int8",
• "collections.OrderedDict",
• "transformers_modules.vinai.PhoGPT-4B-Chat.116013fa63f8c4025739487e1cbff65b7375bbe2.modeling_mpt.MPTForCausalLM",
• "quanto.tensor.qtype.qtype",
• "torch.device",
• "transformers_modules.vinai.PhoGPT-4B-Chat.116013fa63f8c4025739487e1cbff65b7375bbe2.configuration_mpt.MPTConfig",
• "functools.partial",
• "transformers_modules.vinai.PhoGPT-4B-Chat.116013fa63f8c4025739487e1cbff65b7375bbe2.custom_embedding.SharedEmbedding",
• "torch.nn.modules.container.ModuleList",
• "torch.FloatStorage",
• "transformers_modules.vinai.PhoGPT-4B-Chat.116013fa63f8c4025739487e1cbff65b7375bbe2.ffn.MPTMLP",
• "torch._utils._rebuild_tensor_v2",
• "transformers_modules.vinai.PhoGPT-4B-Chat.116013fa63f8c4025739487e1cbff65b7375bbe2.norm.LPLayerNorm"

How to fix it?