Neooooo

/

cs7643_models

like 0

• "torch.nn.modules.linear.Linear",
• "torch._utils._rebuild_parameter_with_state",
• "tokenizers.AddedToken",
• "transformers.models.llama.modeling_llama.LlamaModel",
• "transformers.models.llama.modeling_llama.LlamaForCausalLM",
• "transformers.models.llama.configuration_llama.LlamaConfig",
• "torch.FloatStorage",
• "collections.OrderedDict",
• "torch.nn.modules.container.ModuleList",
• "torch._utils._rebuild_parameter",
• "torch.nn.modules.sparse.Embedding",
• "torch.HalfStorage",
• "__builtin__.set",
• "transformers.modeling_rope_utils._compute_llama3_parameters",
• "transformers.generation.configuration_utils.GenerationConfig",
• "transformers.models.llama.modeling_llama.LlamaMLP",
• "transformers.models.llama.modeling_llama.LlamaRotaryEmbedding",
• "torch.nn.modules.activation.SiLU",
• "tokenizers.models.Model",
• "torch._utils._rebuild_tensor_v2",
• "transformers.tokenization_utils_fast.PreTrainedTokenizerFast",
• "_codecs.encode",
• "tokenizers.Tokenizer",
• "transformers.models.llama.modeling_llama.LlamaRMSNorm",
• "transformers.generation.configuration_utils.CompileConfig",
• "transformers.models.llama.modeling_llama.LlamaDecoderLayer",
• "torch.bfloat16",
• "transformers.models.llama.modeling_llama.LlamaAttention"

How to fix it?