Ctrl+K
- 1.56 kB Add large model.pt file
- 5.23 kB Update README.md
- 660 Bytes Upload 4 files
- 1.46 kB Upload LlamaForCausalLM
- 588 Bytes Upload 4 files
- 234 Bytes Upload LlamaForCausalLM
- 4.65 GB xetUpload LlamaForCausalLM
- 1.05 GB xetUpload LlamaForCausalLM
- model.pt5.7 GB
Detected Pickle imports (5)
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2",
- "torch.HalfStorage",
- "torch.ByteStorage",
- "torch.FloatStorage"
xetUpload model.pt with huggingface_hub - 597 Bytes Upload 4 files
- 132 kB Upload LlamaForCausalLM
- multilingual_transformer_step_30000_torchscript.pt2.1 GB
Detected Pickle imports (227)
- "__torch__.torch.nn.modules.linear.___torch_mangle_87.Linear",
- "__torch__.___torch_mangle_9.MultiHeadAttention",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_53.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_83.Linear",
- "__torch__.___torch_mangle_72.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_161.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_57.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_193.Linear",
- "__torch__.___torch_mangle_192.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_162.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_113.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_202.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_66.Linear",
- "__torch__.torch.nn.modules.container.___torch_mangle_204.ModuleList",
- "__torch__.torch.nn.modules.linear.___torch_mangle_11.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_118.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_65.Linear",
- "__torch__.torch.nn.modules.sparse.___torch_mangle_76.Embedding",
- "__torch__.torch.nn.modules.linear.___torch_mangle_131.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_137.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_151.Linear",
- "__torch__.___torch_mangle_81.MultiHeadAttention",
- "__torch__.___torch_mangle_168.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_183.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_196.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_199.Linear",
- "__torch__.___torch_mangle_34.EncoderLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_145.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_172.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_15.Linear",
- "__torch__.___torch_mangle_69.MultiHeadAttention",
- "__torch__.___torch_mangle_133.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_174.Linear",
- "__torch__.___torch_mangle_155.DecoderLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_177.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_26.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_28.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_0.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_23.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_2.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_36.Linear",
- "__torch__.___torch_mangle_181.MultiHeadAttention",
- "__torch__.___torch_mangle_96.MultiHeadAttention",
- "__torch__.___torch_mangle_139.DecoderLayer",
- "torch._utils._rebuild_tensor_v2",
- "__torch__.torch.nn.modules.linear.___torch_mangle_67.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_88.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_180.Linear",
- "__torch__.___torch_mangle_86.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_70.Linear",
- "__torch__.___torch_mangle_107.DecoderLayer",
- "__torch__.___torch_mangle_136.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_163.Linear",
- "__torch__.___torch_mangle_176.MultiHeadAttention",
- "__torch__.___torch_mangle_112.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_38.Linear",
- "__torch__.___torch_mangle_62.FeedForward",
- "__torch__.___torch_mangle_12.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_50.Linear",
- "__torch__.___torch_mangle_44.EncoderLayer",
- "__torch__.___torch_mangle_144.MultiHeadAttention",
- "__torch__.___torch_mangle_184.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_77.Linear",
- "__torch__.___torch_mangle_52.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_143.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_147.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_110.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_80.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_13.LayerNorm",
- "__torch__.___torch_mangle_89.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_46.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_167.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_8.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_78.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_138.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_37.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_47.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_173.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_75.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_63.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_90.LayerNorm",
- "__torch__.___torch_mangle_101.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_182.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_164.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_185.LayerNorm",
- "__torch__.___torch_mangle_29.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_141.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_170.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_27.Linear",
- "__torch__.___torch_mangle_49.MultiHeadAttention",
- "__torch__.___torch_mangle_187.DecoderLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_178.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_205.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_3.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_68.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_159.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_95.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_98.Linear",
- "__torch__.___torch_mangle_117.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_111.Linear",
- "__torch__.___torch_mangle_152.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_40.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_156.Linear",
- "__torch__.torch.nn.modules.sparse.Embedding",
- "__torch__.torch.nn.modules.linear.___torch_mangle_85.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_153.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_10.Linear",
- "__torch__.___torch_mangle_74.EncoderLayer",
- "__torch__.___torch_mangle_171.DecoderLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_103.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_108.Linear",
- "__torch__.___torch_mangle_128.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_18.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_31.Linear",
- "__torch__.___torch_mangle_160.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_125.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_126.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_190.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_109.Linear",
- "__torch__.___torch_mangle_24.EncoderLayer",
- "__torch__.torch.nn.modules.linear.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_16.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_105.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_166.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_30.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_122.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_100.Linear",
- "__torch__.___torch_mangle_39.MultiHeadAttention",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_201.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_189.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_55.Linear",
- "__torch__.DecoderLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_94.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_130.Linear",
- "__torch__.___torch_mangle_42.FeedForward",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_106.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_114.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_198.Linear",
- "__torch__.EncoderLayer",
- "__torch__.___torch_mangle_22.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_140.Linear",
- "__torch__.___torch_mangle_200.FeedForward",
- "__torch__.CustomEncoder",
- "__torch__.___torch_mangle_19.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_48.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_41.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_43.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_56.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_119.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_99.Linear",
- "__torch__.CustomDecoder",
- "__torch__.___torch_mangle_14.EncoderLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_17.Linear",
- "__torch__.___torch_mangle_123.DecoderLayer",
- "__torch__.___torch_mangle_32.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_6.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_7.Linear",
- "__torch__.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_20.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_169.LayerNorm",
- "__torch__.___torch_mangle_54.EncoderLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_93.Linear",
- "__torch__.___torch_mangle_203.DecoderLayer",
- "__torch__.___torch_mangle_197.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_124.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_175.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_154.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_116.Linear",
- "__torch__.___torch_mangle_149.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_92.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_188.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_51.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_45.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_82.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_61.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_150.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_35.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_127.Linear",
- "__torch__.___torch_mangle_165.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_58.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_79.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_146.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_4.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_115.Linear",
- "__torch__.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_71.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_195.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_121.LayerNorm",
- "torch.FloatStorage",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_33.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_84.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_21.Linear",
- "__torch__.___torch_mangle_64.EncoderLayer",
- "__torch__.CustomTransformer",
- "__torch__.___torch_mangle_59.MultiHeadAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_158.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_97.Linear",
- "collections.OrderedDict",
- "__torch__.torch.nn.modules.linear.___torch_mangle_132.Linear",
- "__torch__.torch.nn.modules.normalization.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_142.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_157.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_102.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_91.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_134.Linear",
- "__torch__.___torch_mangle_120.FeedForward",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_73.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_135.Linear",
- "__torch__.torch.nn.modules.container.ModuleList",
- "__torch__.torch.nn.modules.linear.___torch_mangle_148.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_179.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_194.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_191.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_60.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_186.LayerNorm",
- "__torch__.___torch_mangle_104.FeedForward",
- "__torch__.torch.nn.modules.linear.___torch_mangle_5.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_25.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_1.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_129.Linear",
- "torch._utils._rebuild_tensor_v2",
- "torch.DoubleStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.jit._pickle.restore_type_tag",
- "torch.LongStorage"
xetUpload multilingual_transformer_step_30000_torchscript.pt with huggingface_hub - 9.09 MB added missing tokenizer
- 635 Bytes Upload 4 files
- 55.4 kB added missing tokenizer