PrunaAI

/

tiiuae-falcon-11B-QUANTO-int8bit-smashed

like 0

Follow

Pruna AI 8

• "torch.FloatStorage",
• "torch.nn.modules.normalization.LayerNorm",
• "transformers.generation.configuration_utils.GenerationConfig",
• "__builtin__.set",
• "torch.nn.modules.container.ModuleList",
• "transformers_modules.tiiuae.falcon-11B.066e3bf4e2d9aaeefa129af0a6d39727d27816b3.modeling_falcon.FalconModel",
• "torch._utils._rebuild_tensor_v2",
• "torch.bfloat16",
• "torch.nn.modules.sparse.Embedding",
• "torch.nn.modules.dropout.Dropout",
• "transformers_modules.tiiuae.falcon-11B.066e3bf4e2d9aaeefa129af0a6d39727d27816b3.modeling_falcon.FalconForCausalLM",
• "quanto.nn.qlinear.QLinear",
• "torch.int8",
• "collections.OrderedDict",
• "quanto.tensor.qtype.qtype",
• "transformers_modules.tiiuae.falcon-11B.066e3bf4e2d9aaeefa129af0a6d39727d27816b3.modeling_falcon.FalconMLP",
• "transformers_modules.tiiuae.falcon-11B.066e3bf4e2d9aaeefa129af0a6d39727d27816b3.modeling_falcon.FalconAttention",
• "transformers_modules.tiiuae.falcon-11B.066e3bf4e2d9aaeefa129af0a6d39727d27816b3.modeling_falcon.FalconDecoderLayer",
• "transformers_modules.tiiuae.falcon-11B.066e3bf4e2d9aaeefa129af0a6d39727d27816b3.modeling_falcon.FalconRotaryEmbedding",
• "torch.device",
• "transformers_modules.tiiuae.falcon-11B.066e3bf4e2d9aaeefa129af0a6d39727d27816b3.configuration_falcon.FalconConfig",
• "torch._utils._rebuild_parameter",
• "torch.nn.modules.activation.GELU",
• "torch.BFloat16Storage"

How to fix it?