dahara1

/

llama3.1-8b-Instruct-awq

like 3

• "modeling_llama_amd.LlamaModel",
• "torch.Size",
• "collections.OrderedDict",
• "modeling_llama_amd.LlamaAttention",
• "torch.bfloat16",
• "__builtin__.set",
• "torch.nn.modules.activation.SiLU",
• "torch._utils._rebuild_parameter",
• "transformers.models.llama.configuration_llama.LlamaConfig",
• "torch._utils._rebuild_tensor_v2",
• "qlinear.QLinearPerGrp",
• "torch.BFloat16Storage",
• "torch.nn.modules.sparse.Embedding",
• "torch.nn.modules.container.ModuleList",
• "modeling_llama_amd.LlamaDecoderLayer",
• "modeling_llama_amd.LlamaMLP",
• "transformers.generation.configuration_utils.GenerationConfig",
• "modeling_llama_amd.LlamaForCausalLM",
• "torch.nn.modules.linear.Linear",
• "torch.CharStorage",
• "modeling_llama_amd.LlamaRMSNorm",
• "modeling_llama_amd.LlamaRotaryEmbedding",
• "torch.FloatStorage"

How to fix it?