HuangRT

/

LLMPruner_prune_log

like 0

• "transformers.models.qwen2.modeling_qwen2.Qwen2MLP",
• "transformers.modeling_rope_utils._compute_default_rope_parameters",
• "transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast",
• "torch.nn.modules.linear.Linear",
• "tokenizers.models.Model",
• "transformers.generation.configuration_utils.CompileConfig",
• "transformers.generation.configuration_utils.GenerationConfig",
• "tokenizers.AddedToken",
• "_codecs.encode",
• "__builtin__.set",
• "torch._utils._rebuild_parameter",
• "transformers.models.qwen2.modeling_qwen2.Qwen2Model",
• "collections.OrderedDict",
• "torch.FloatStorage",
• "torch.nn.modules.activation.SiLU",
• "transformers.models.qwen2.modeling_qwen2.Qwen2DecoderLayer",
• "tokenizers.Tokenizer",
• "torch.nn.modules.sparse.Embedding",
• "torch._utils._rebuild_tensor_v2",
• "transformers.models.qwen2.modeling_qwen2.Qwen2Attention",
• "transformers.models.qwen2.modeling_qwen2.Qwen2RotaryEmbedding",
• "torch.nn.modules.container.ModuleList",
• "torch.bfloat16",
• "transformers.models.qwen2.configuration_qwen2.Qwen2Config",
• "transformers.models.qwen2.modeling_qwen2.Qwen2RMSNorm",
• "transformers.models.qwen2.modeling_qwen2.Qwen2ForCausalLM",
• "torch.HalfStorage"

How to fix it?