PrunaAI

/

google-recurrentgemma-2b-it-QUANTO-int8bit-smashed

like 0

Follow

Pruna AI 260

• "quanto.nn.qlinear.QLinear",
• "torch.BFloat16Storage",
• "torch._utils._rebuild_parameter",
• "torch.nn.modules.conv.Conv1d",
• "transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaMlp",
• "collections.OrderedDict",
• "__builtin__.set",
• "transformers.models.recurrent_gemma.configuration_recurrent_gemma.RecurrentGemmaConfig",
• "transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaDecoderLayer",
• "torch.nn.modules.sparse.Embedding",
• "transformers.activations.PytorchGELUTanh",
• "transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaRglru",
• "torch.device",
• "torch._utils._rebuild_tensor_v2",
• "transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaModel",
• "torch.int8",
• "transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaRecurrentBlock",
• "torch.nn.modules.container.ModuleList",
• "transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaSdpaAttention",
• "torch.bfloat16",
• "transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaRotaryEmbedding",
• "transformers.generation.configuration_utils.GenerationConfig",
• "transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaRMSNorm",
• "torch.FloatStorage",
• "transformers.models.recurrent_gemma.modeling_recurrent_gemma.RecurrentGemmaForCausalLM",
• "quanto.tensor.qtype.qtype"

How to fix it?