PrunaAI

/

facebook-opt-125m-QUANTO-int4bit-smashed

like 0

Follow

Pruna AI 136

• "torch.int8",
• "transformers.generation.configuration_utils.GenerationConfig",
• "transformers.models.opt.modeling_opt.OPTAttention",
• "transformers.models.opt.configuration_opt.OPTConfig",
• "quanto.tensor.qtype.qtype",
• "torch._utils._rebuild_parameter",
• "torch.nn.modules.container.ModuleList",
• "collections.OrderedDict",
• "transformers.models.opt.modeling_opt.OPTModel",
• "transformers.models.opt.modeling_opt.OPTDecoder",
• "torch.nn.modules.sparse.Embedding",
• "transformers.models.opt.modeling_opt.OPTDecoderLayer",
• "torch.float16",
• "__builtin__.set",
• "quanto.nn.qlinear.QLinear",
• "torch._utils._rebuild_tensor_v2",
• "transformers.models.opt.modeling_opt.OPTLearnedPositionalEmbedding",
• "torch.device",
• "torch.FloatStorage",
• "torch.HalfStorage",
• "torch.nn.modules.activation.ReLU",
• "torch.nn.modules.normalization.LayerNorm",
• "transformers.models.opt.modeling_opt.OPTForCausalLM"

How to fix it?