PrunaAI

/

DAMO-NLP-SG-VideoLLaMA2-7B-16F-QUANTO-int2bit-smashed

like 0

• "quanto.tensor.qtype.qtype",
• "torch.device",
• "transformers.models.mistral.modeling_mistral.MistralDecoderLayer",
• "torch.FloatStorage",
• "torch._utils._rebuild_tensor_v2",
• "transformers.generation.configuration_utils.GenerationConfig",
• "transformers.models.mistral.modeling_mistral.MistralModel",
• "transformers.models.mistral.modeling_mistral.MistralSdpaAttention",
• "__builtin__.set",
• "torch._utils._rebuild_parameter",
• "torch.int8",
• "transformers.models.mistral.modeling_mistral.MistralRotaryEmbedding",
• "torch.nn.modules.sparse.Embedding",
• "transformers.models.mistral.configuration_mistral.MistralConfig",
• "collections.OrderedDict",
• "quanto.nn.qlinear.QLinear",
• "transformers.models.mistral.modeling_mistral.MistralRMSNorm",
• "transformers.models.mistral.modeling_mistral.MistralMLP",
• "torch.bfloat16",
• "torch.nn.modules.activation.SiLU",
• "torch.BFloat16Storage",
• "transformers.models.mistral.modeling_mistral.MistralForCausalLM",
• "torch.nn.modules.container.ModuleList"

How to fix it?