PrunaAI

/

stabilityai-japanese-stablelm-3b-4e1t-instruct-QUANTO-int4bit-smashed

like 0

Follow

Pruna AI 112

• "transformers.generation.configuration_utils.GenerationConfig",
• "torch.nn.modules.activation.SiLU",
• "quanto.nn.qlinear.QLinear",
• "quanto.tensor.qtype.qtype",
• "torch.int8",
• "transformers_modules.stabilityai.japanese-stablelm-3b-4e1t-instruct.4bcd24cf3397c4563062e7d2897c2fa5ea16acc2.configuration_stablelm_epoch.StableLMEpochConfig",
• "__builtin__.set",
• "torch.nn.modules.normalization.LayerNorm",
• "collections.OrderedDict",
• "transformers_modules.stabilityai.japanese-stablelm-3b-4e1t-instruct.4bcd24cf3397c4563062e7d2897c2fa5ea16acc2.modeling_stablelm_epoch.RotaryEmbedding",
• "torch._utils._rebuild_tensor_v2",
• "torch.FloatStorage",
• "torch.bfloat16",
• "transformers_modules.stabilityai.japanese-stablelm-3b-4e1t-instruct.4bcd24cf3397c4563062e7d2897c2fa5ea16acc2.modeling_stablelm_epoch.DecoderLayer",
• "transformers_modules.stabilityai.japanese-stablelm-3b-4e1t-instruct.4bcd24cf3397c4563062e7d2897c2fa5ea16acc2.modeling_stablelm_epoch.MLP",
• "torch.nn.modules.container.ModuleList",
• "torch.nn.modules.sparse.Embedding",
• "torch._utils._rebuild_parameter",
• "torch.device",
• "torch.BFloat16Storage",
• "transformers_modules.stabilityai.japanese-stablelm-3b-4e1t-instruct.4bcd24cf3397c4563062e7d2897c2fa5ea16acc2.modeling_stablelm_epoch.StableLMEpochModel",
• "transformers_modules.stabilityai.japanese-stablelm-3b-4e1t-instruct.4bcd24cf3397c4563062e7d2897c2fa5ea16acc2.modeling_stablelm_epoch.Attention",
• "transformers_modules.stabilityai.japanese-stablelm-3b-4e1t-instruct.4bcd24cf3397c4563062e7d2897c2fa5ea16acc2.modeling_stablelm_epoch.StableLMEpochForCausalLM"

How to fix it?