PrunaAI

/

openbmb-MiniCPM-2B-sft-bf16-QUANTO-float8bit-smashed

like 0

Follow

Pruna AI 176

• "transformers_modules.openbmb.MiniCPM-2B-sft-bf16.79fbb1db171e6d8bf77cdb0a94076a43003abd9e.modeling_minicpm.MiniCPMFlashAttention2",
• "torch.nn.modules.activation.SiLU",
• "transformers_modules.openbmb.MiniCPM-2B-sft-bf16.79fbb1db171e6d8bf77cdb0a94076a43003abd9e.modeling_minicpm.MiniCPMModel",
• "torch.bfloat16",
• "transformers_modules.openbmb.MiniCPM-2B-sft-bf16.79fbb1db171e6d8bf77cdb0a94076a43003abd9e.modeling_minicpm.MiniCPMForCausalLM",
• "transformers_modules.openbmb.MiniCPM-2B-sft-bf16.79fbb1db171e6d8bf77cdb0a94076a43003abd9e.configuration_minicpm.MiniCPMConfig",
• "torch._utils._rebuild_parameter",
• "torch._utils._rebuild_tensor_v2",
• "quanto.nn.qlinear.QLinear",
• "transformers.generation.configuration_utils.GenerationConfig",
• "collections.OrderedDict",
• "__builtin__.set",
• "quanto.tensor.qtype.qtype",
• "torch.nn.modules.container.ModuleList",
• "transformers_modules.openbmb.MiniCPM-2B-sft-bf16.79fbb1db171e6d8bf77cdb0a94076a43003abd9e.modeling_minicpm.MiniCPMRMSNorm",
• "transformers_modules.openbmb.MiniCPM-2B-sft-bf16.79fbb1db171e6d8bf77cdb0a94076a43003abd9e.modeling_minicpm.MiniCPMMLP",
• "torch.BFloat16Storage",
• "torch.FloatStorage",
• "transformers_modules.openbmb.MiniCPM-2B-sft-bf16.79fbb1db171e6d8bf77cdb0a94076a43003abd9e.modeling_minicpm.MiniCPMRotaryEmbedding",
• "torch.nn.modules.sparse.Embedding",
• "transformers_modules.openbmb.MiniCPM-2B-sft-bf16.79fbb1db171e6d8bf77cdb0a94076a43003abd9e.modeling_minicpm.MiniCPMDecoderLayer",
• "torch.float8_e4m3fn",
• "torch.device"

How to fix it?