PrunaAI

/

MaziyarPanahi-Phi-3-mini-4k-instruct-v0.3-QUANTO-float8bit-smashed

like 0

• "torch.nn.modules.activation.SiLU",
• "transformers_modules.microsoft.Phi-3-mini-4k-instruct.ff07dc01615f8113924aed013115ab2abd32115b.modeling_phi3.Phi3ForCausalLM",
• "torch.bfloat16",
• "transformers_modules.microsoft.Phi-3-mini-4k-instruct.ff07dc01615f8113924aed013115ab2abd32115b.configuration_phi3.Phi3Config",
• "transformers_modules.microsoft.Phi-3-mini-4k-instruct.ff07dc01615f8113924aed013115ab2abd32115b.modeling_phi3.Phi3Model",
• "transformers_modules.microsoft.Phi-3-mini-4k-instruct.ff07dc01615f8113924aed013115ab2abd32115b.modeling_phi3.Phi3RMSNorm",
• "transformers_modules.microsoft.Phi-3-mini-4k-instruct.ff07dc01615f8113924aed013115ab2abd32115b.modeling_phi3.Phi3Attention",
• "torch._utils._rebuild_parameter",
• "torch._utils._rebuild_tensor_v2",
• "transformers_modules.microsoft.Phi-3-mini-4k-instruct.ff07dc01615f8113924aed013115ab2abd32115b.modeling_phi3.Phi3DecoderLayer",
• "quanto.nn.qlinear.QLinear",
• "transformers.generation.configuration_utils.GenerationConfig",
• "collections.OrderedDict",
• "__builtin__.set",
• "quanto.tensor.qtype.qtype",
• "torch.nn.modules.container.ModuleList",
• "torch.BFloat16Storage",
• "torch.FloatStorage",
• "torch.nn.modules.sparse.Embedding",
• "transformers_modules.microsoft.Phi-3-mini-4k-instruct.ff07dc01615f8113924aed013115ab2abd32115b.modeling_phi3.Phi3RotaryEmbedding",
• "torch.nn.modules.dropout.Dropout",
• "transformers_modules.microsoft.Phi-3-mini-4k-instruct.ff07dc01615f8113924aed013115ab2abd32115b.modeling_phi3.Phi3MLP",
• "torch.float8_e4m3fn",
• "torch.device"

How to fix it?