Create README.md
922ce73
-
1.52 kB
initial commit
-
53 Bytes
Create README.md
polyglot-ko-1_3b-quant.pt
Detected Pickle imports (457)
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_526.LinearPackedParams",
- "__torch__.transformers.activations.___torch_mangle_462.GELUActivation",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_529.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_620.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_787.GPTNeoXMLP",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_857.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_735.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_801.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_781.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_819.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_569.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_614.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_737.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_689.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_661.GPTNeoXMLP",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_443.Linear",
- "__torch__.transformers.activations.___torch_mangle_840.GELUActivation",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_818.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_810.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_476.LinearPackedParams",
- "__torch__.torch.nn.modules.container.___torch_mangle_861.ModuleList",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_727.GPTNeoXAttention",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_744.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_531.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_738.Dropout",
- "__torch__.transformers.activations.___torch_mangle_606.GELUActivation",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_482.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_596.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_527.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_463.GPTNeoXMLP",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_791.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_726.Dropout",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_555.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_815.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_576.Dropout",
- "__torch__.transformers.activations.___torch_mangle_822.GELUActivation",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_450.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_693.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_764.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_465.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_483.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_563.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_677.Linear",
- "torch._utils._rebuild_qtensor",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_863.GPTNeoXModel",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_546.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_779.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_855.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_690.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_507.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_664.LayerNorm",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_824.GPTNeoXLayer",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_665.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_583.GPTNeoXAttention",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_673.GPTNeoXAttention",
- "torch.per_tensor_affine",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_553.GPTNeoXMLP",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_700.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_862.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_771.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_856.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_717.LayerNorm",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_773.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_691.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_441.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_833.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_631.RotaryEmbedding",
- "__torch__.transformers.activations.___torch_mangle_750.GELUActivation",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_817.GPTNeoXAttention",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_611.Dropout",
- "torch._utils._rebuild_tensor_v2",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_566.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_755.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_838.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_777.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_494.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_575.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_473.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_523.RotaryEmbedding",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_484.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_459.Linear",
- "__torch__.transformers.activations.___torch_mangle_444.GELUActivation",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_849.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_681.LayerNorm",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_607.GPTNeoXMLP",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_832.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_558.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_715.GPTNeoXMLP",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_451.RotaryEmbedding",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_762.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_648.Dropout",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_448.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_538.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_736.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_437.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_644.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_728.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_667.RotaryEmbedding",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_584.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_722.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_864.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_844.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_712.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_836.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_565.GPTNeoXAttention",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_582.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_866.GPTNeoXForCausalLM",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_823.GPTNeoXMLP",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_479.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_578.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_453.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_821.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_612.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_672.Dropout",
- "__torch__.torch.classes.quantized.LinearPackedParamsBase",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_633.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_703.RotaryEmbedding",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_590.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_639.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_641.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_457.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_455.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_541.RotaryEmbedding",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_540.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_581.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_828.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_428.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_656.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_746.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_544.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_825.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_850.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_740.LinearPackedParams",
- "__torch__.transformers.activations.___torch_mangle_858.GELUActivation",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_767.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_809.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_487.RotaryEmbedding",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_490.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_802.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_485.Dropout",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_772.LayerNorm",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_464.GPTNeoXLayer",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_829.RotaryEmbedding",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_559.RotaryEmbedding",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_799.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_765.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_587.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_440.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_481.GPTNeoXMLP",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_589.GPTNeoXMLP",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_749.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_446.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_653.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_702.Dropout",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_753.LayerNorm",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_433.RotaryEmbedding",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_651.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_733.GPTNeoXMLP",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_730.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_697.GPTNeoXMLP",
- "__torch__.transformers.activations.___torch_mangle_588.GELUActivation",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_670.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_513.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_562.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_743.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_597.Linear",
- "__torch__.transformers.activations.___torch_mangle_642.GELUActivation",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_517.GPTNeoXMLP",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_432.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_704.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_585.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_748.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_705.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_695.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_442.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_835.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_731.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_729.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_694.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_860.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_599.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_720.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_456.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_676.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_701.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_725.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_472.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_608.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_848.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_692.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_447.LayerNorm",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_469.RotaryEmbedding",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_466.LayerNorm",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_756.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_685.RotaryEmbedding",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_721.RotaryEmbedding",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_758.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_854.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_573.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_502.LayerNorm",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_577.RotaryEmbedding",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_524.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_491.Linear",
- "__torch__.transformers.activations.___torch_mangle_570.GELUActivation",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_830.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_800.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_713.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_605.Linear",
- "torch.FloatStorage",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_629.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_504.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_852.Dropout",
- "__torch__.transformers.activations.___torch_mangle_678.GELUActivation",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_602.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_662.GPTNeoXLayer",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_798.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_671.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_813.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_572.GPTNeoXLayer",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_492.Dropout",
- "__torch__.transformers.activations.___torch_mangle_516.GELUActivation",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_532.LinearPackedParams",
- "torch.QInt8Storage",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_711.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_571.GPTNeoXMLP",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_847.RotaryEmbedding",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_734.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_658.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_623.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_843.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_568.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_488.LinearPackedParams",
- "__torch__.transformers.activations.___torch_mangle_804.GELUActivation",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_519.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_634.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_774.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_557.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_545.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_496.LinearPackedParams",
- "__torch__.transformers.activations.___torch_mangle_498.GELUActivation",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_621.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_788.GPTNeoXLayer",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_841.GPTNeoXMLP",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_745.GPTNeoXAttention",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_501.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_640.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_635.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_752.GPTNeoXLayer",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_789.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_782.LinearPackedParams",
- "__torch__.transformers.activations.___torch_mangle_732.GELUActivation",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_794.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_537.LayerNorm",
- "__torch__.transformers.activations.___torch_mangle_768.GELUActivation",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_500.GPTNeoXLayer",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_682.LayerNorm",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_630.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_509.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_792.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_549.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_495.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_793.RotaryEmbedding",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_769.GPTNeoXMLP",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_625.GPTNeoXMLP",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_643.GPTNeoXMLP",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_528.Dropout",
- "__torch__.transformers.activations.___torch_mangle_552.GELUActivation",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_760.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_593.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_493.GPTNeoXAttention",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_808.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_508.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_834.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_561.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_759.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_757.RotaryEmbedding",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_741.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_770.GPTNeoXLayer",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_468.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_853.GPTNeoXAttention",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_613.RotaryEmbedding",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_650.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_512.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_467.Dropout",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_592.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_761.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_511.GPTNeoXAttention",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_807.LayerNorm",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_806.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_436.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_430.LayerNorm",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_683.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_530.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_503.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_601.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_478.LinearPackedParams",
- "__torch__.transformers.activations.___torch_mangle_786.GELUActivation",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_797.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_461.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_687.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_539.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_439.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_851.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_778.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_574.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_543.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_486.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_709.GPTNeoXAttention",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_663.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_776.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_505.RotaryEmbedding",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_780.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_438.Dropout",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_645.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_707.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_766.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_827.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_719.Dropout",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_520.LayerNorm",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_775.RotaryEmbedding",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_657.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_477.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_610.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_638.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_460.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_739.RotaryEmbedding",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_626.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_603.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_698.GPTNeoXLayer",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_536.GPTNeoXLayer",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_564.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_535.GPTNeoXMLP",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_816.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_474.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_560.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_632.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_784.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_668.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_837.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_723.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_542.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_795.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_431.Dropout",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_515.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_652.LinearPackedParams",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_647.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_686.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_674.LinearPackedParams",
- "__torch__.torch.nn.modules.sparse.___torch_mangle_427.Embedding",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_812.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_627.LayerNorm",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_649.RotaryEmbedding",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_628.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_489.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_452.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_434.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_586.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_518.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_616.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_548.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_814.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_811.RotaryEmbedding",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_790.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_604.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_646.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_591.LayerNorm",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_742.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_688.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_669.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_506.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_497.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_598.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_679.GPTNeoXMLP",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_550.LinearPackedParams",
- "__torch__.transformers.activations.___torch_mangle_660.GELUActivation",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_654.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_805.GPTNeoXMLP",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_429.LayerNorm",
- "__torch__.transformers.activations.___torch_mangle_696.GELUActivation",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_554.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_622.LinearPackedParams",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_754.LayerNorm",
- "collections.OrderedDict",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_699.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_579.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_510.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_859.GPTNeoXMLP",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_525.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_595.RotaryEmbedding",
- "torch.BoolStorage",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_718.LayerNorm",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_618.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_470.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_514.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_842.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_783.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_533.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_708.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_666.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_763.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_785.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_522.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_706.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_659.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_675.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_865.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_636.Dropout",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_826.LayerNorm",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_547.GPTNeoXAttention",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_680.GPTNeoXLayer",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_796.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_475.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_454.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_499.GPTNeoXMLP",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_609.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_803.Linear",
- "__torch__.transformers.activations.___torch_mangle_714.GELUActivation",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_655.GPTNeoXAttention",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_445.GPTNeoXMLP",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_458.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_615.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_710.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_831.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_435.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_556.LayerNorm",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_567.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_845.Dropout",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_619.GPTNeoXAttention",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_551.Linear",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_580.LinearPackedParams",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_471.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_617.Linear",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_747.Linear",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_637.GPTNeoXAttention",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_716.GPTNeoXLayer",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_449.Dropout",
- "__torch__.transformers.activations.___torch_mangle_480.GELUActivation",
- "__torch__.torch.ao.nn.quantized.dynamic.modules.linear.___torch_mangle_839.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_684.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_600.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_594.Dropout",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_724.LinearPackedParams",
- "__torch__.transformers.activations.___torch_mangle_534.GELUActivation",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_846.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_521.Dropout",
- "__torch__.transformers.activations.___torch_mangle_624.GELUActivation",
- "__torch__.torch.ao.nn.quantized.modules.linear.___torch_mangle_820.LinearPackedParams",
- "__torch__.transformers.models.gpt_neox.modeling_gpt_neox.___torch_mangle_751.GPTNeoXMLP",
- "torch.DoubleStorage",
- "torch.LongStorage",
- "collections.OrderedDict",
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.jit._pickle.restore_type_tag",
- "collections.OrderedDict",
- "torch.LongStorage",
- "torch._utils._rebuild_tensor_v2"
How to fix it?
1.62 GB
Initial commit