PrunaAI

/

lex-hue-Delexa-7b-QUANTO-float8bit-smashed

like 0

Follow

Pruna AI 118

• "transformers_modules.lex-hue.Delexa-7b.93916358b007d33ce58baf3f02e480bd90532be6.modeling_mistral_yarn.MistralYaRNScaledRotaryEmbedding",
• "torch.float16",
• "transformers.generation.configuration_utils.GenerationConfig",
• "transformers_modules.lex-hue.Delexa-7b.93916358b007d33ce58baf3f02e480bd90532be6.configuration_mistral.MistralConfig",
• "transformers_modules.lex-hue.Delexa-7b.93916358b007d33ce58baf3f02e480bd90532be6.modeling_mistral_yarn.MistralForCausalLM",
• "torch.HalfStorage",
• "torch._utils._rebuild_parameter",
• "torch.float8_e4m3fn",
• "transformers_modules.lex-hue.Delexa-7b.93916358b007d33ce58baf3f02e480bd90532be6.modeling_mistral_yarn.MistralDecoderLayer",
• "transformers_modules.lex-hue.Delexa-7b.93916358b007d33ce58baf3f02e480bd90532be6.modeling_mistral_yarn.MistralModel",
• "transformers_modules.lex-hue.Delexa-7b.93916358b007d33ce58baf3f02e480bd90532be6.modeling_mistral_yarn.MistralMLP",
• "torch.device",
• "torch.nn.modules.container.ModuleList",
• "__builtin__.set",
• "transformers_modules.lex-hue.Delexa-7b.93916358b007d33ce58baf3f02e480bd90532be6.modeling_mistral_yarn.MistralRMSNorm",
• "torch._utils._rebuild_tensor_v2",
• "transformers_modules.lex-hue.Delexa-7b.93916358b007d33ce58baf3f02e480bd90532be6.modeling_mistral_yarn.MistralAttention",
• "torch.FloatStorage",
• "quanto.nn.qlinear.QLinear",
• "torch.nn.modules.sparse.Embedding",
• "quanto.tensor.qtype.qtype",
• "collections.OrderedDict",
• "torch.nn.modules.activation.SiLU"

How to fix it?