PrunaAI

/

apple-OpenELM-1_1B-Instruct-QUANTO-float8bit-smashed

like 0

Follow

Pruna AI 264

• "transformers.generation.configuration_utils.GenerationConfig",
• "__builtin__.set",
• "torch.FloatStorage",
• "quanto.nn.qlinear.QLinear",
• "torch._utils._rebuild_parameter",
• "transformers_modules.apple.OpenELM-1_1B-Instruct.24982bbb6f27ae000566a6892cf669e0e06278ae.modeling_openelm.OpenELMMultiHeadCausalAttention",
• "transformers_modules.apple.OpenELM-1_1B-Instruct.24982bbb6f27ae000566a6892cf669e0e06278ae.modeling_openelm.OpenELMRMSNorm",
• "quanto.tensor.qtype.qtype",
• "torch.BoolStorage",
• "torch._utils._rebuild_tensor_v2",
• "torch.bfloat16",
• "collections.OrderedDict",
• "transformers_modules.apple.OpenELM-1_1B-Instruct.24982bbb6f27ae000566a6892cf669e0e06278ae.modeling_openelm.OpenELMModel",
• "transformers_modules.apple.OpenELM-1_1B-Instruct.24982bbb6f27ae000566a6892cf669e0e06278ae.modeling_openelm.OpenELMForCausalLM",
• "torch.nn.modules.sparse.Embedding",
• "torch.BFloat16Storage",
• "torch.nn.modules.activation.SiLU",
• "transformers_modules.apple.OpenELM-1_1B-Instruct.24982bbb6f27ae000566a6892cf669e0e06278ae.modeling_openelm.OpenELMRotaryEmbedding",
• "torch.device",
• "transformers_modules.apple.OpenELM-1_1B-Instruct.24982bbb6f27ae000566a6892cf669e0e06278ae.configuration_openelm.OpenELMConfig",
• "torch.nn.modules.container.ModuleList",
• "transformers_modules.apple.OpenELM-1_1B-Instruct.24982bbb6f27ae000566a6892cf669e0e06278ae.modeling_openelm.OpenELMDecoderLayer",
• "transformers_modules.apple.OpenELM-1_1B-Instruct.24982bbb6f27ae000566a6892cf669e0e06278ae.modeling_openelm.OpenELMFeedForwardNetwork",
• "torch.float8_e4m3fn"

How to fix it?