biankavm

/

Llama1-NLP

like 0

• "collections.OrderedDict",
• "__main__.RoPEMaskedMultiheadAttention",
• "__main__.Llama",
• "torch.nn.modules.sparse.Embedding",
• "__main__.SwiGLU",
• "__main__.NormalizacaoRMS",
• "torch.FloatStorage",
• "__main__.TransformerBlockLlama",
• "torch._utils._rebuild_parameter",
• "torch.nn.modules.linear.Linear",
• "torch._utils._rebuild_tensor_v2",
• "__main__.RoPEMaskedAttentionHead",
• "torch.nn.modules.container.ModuleList",
• "__builtin__.set",
• "torch.nn.modules.dropout.Dropout",
• "torch.nn.modules.container.Sequential"

How to fix it?