PrunaAI

/

llmware-bling-stable-lm-3b-4e1t-v0-QUANTO-float8bit-smashed

like 0

Follow

Pruna AI 112

• "torch.nn.modules.normalization.LayerNorm",
• "torch._utils._rebuild_tensor_v2",
• "torch.BFloat16Storage",
• "transformers_modules.llmware.bling-stable-lm-3b-4e1t-v0.1b1d3bf057a6e98c875a55aa6062cdfadc32ba8e.modeling_stablelm_epoch.Attention",
• "torch._utils._rebuild_parameter",
• "transformers_modules.llmware.bling-stable-lm-3b-4e1t-v0.1b1d3bf057a6e98c875a55aa6062cdfadc32ba8e.modeling_stablelm_epoch.StableLMEpochForCausalLM",
• "__builtin__.set",
• "collections.OrderedDict",
• "torch.nn.modules.container.ModuleList",
• "transformers.generation.configuration_utils.GenerationConfig",
• "transformers_modules.llmware.bling-stable-lm-3b-4e1t-v0.1b1d3bf057a6e98c875a55aa6062cdfadc32ba8e.configuration_stablelm_epoch.StableLMEpochConfig",
• "transformers_modules.llmware.bling-stable-lm-3b-4e1t-v0.1b1d3bf057a6e98c875a55aa6062cdfadc32ba8e.modeling_stablelm_epoch.DecoderLayer",
• "transformers_modules.llmware.bling-stable-lm-3b-4e1t-v0.1b1d3bf057a6e98c875a55aa6062cdfadc32ba8e.modeling_stablelm_epoch.RotaryEmbedding",
• "quanto.tensor.qtype.qtype",
• "torch.float8_e4m3fn",
• "torch.nn.modules.activation.SiLU",
• "torch.device",
• "transformers_modules.llmware.bling-stable-lm-3b-4e1t-v0.1b1d3bf057a6e98c875a55aa6062cdfadc32ba8e.modeling_stablelm_epoch.StableLMEpochModel",
• "torch.nn.modules.sparse.Embedding",
• "quanto.nn.qlinear.QLinear",
• "torch.bfloat16",
• "torch.FloatStorage",
• "transformers_modules.llmware.bling-stable-lm-3b-4e1t-v0.1b1d3bf057a6e98c875a55aa6062cdfadc32ba8e.modeling_stablelm_epoch.MLP"

How to fix it?