PrunaAI

/

dicta-il-dictalm-7b-QUANTO-float8bit-smashed

like 0

Follow

Pruna AI 136

• "torch._C._nn.gelu",
• "torch.nn.modules.sparse.Embedding",
• "__builtin__.set",
• "transformers_modules.dicta-il.dictalm-7b.c233431901e34e82235e058ff75053a292547e79.modeling_megatron_gpt.MegatronGPTMLP",
• "torch.device",
• "transformers_modules.dicta-il.dictalm-7b.c233431901e34e82235e058ff75053a292547e79.configuration_megatron_gpt.MegatronGPTConfig",
• "torch.float16",
• "torch._utils._rebuild_tensor_v2",
• "torch.nn.modules.dropout.Dropout",
• "transformers_modules.dicta-il.dictalm-7b.c233431901e34e82235e058ff75053a292547e79.modeling_megatron_gpt.MegatronGPTLayer",
• "transformers_modules.dicta-il.dictalm-7b.c233431901e34e82235e058ff75053a292547e79.modeling_megatron_gpt.MegatronGPTAttention",
• "transformers_modules.dicta-il.dictalm-7b.c233431901e34e82235e058ff75053a292547e79.modeling_megatron_gpt.MegatronGPTLayerNorm",
• "collections.OrderedDict",
• "torch.HalfStorage",
• "torch.nn.modules.container.ModuleList",
• "torch.BoolStorage",
• "torch.FloatStorage",
• "transformers_modules.dicta-il.dictalm-7b.c233431901e34e82235e058ff75053a292547e79.modeling_megatron_gpt.MegatronGPTForCausalLM",
• "transformers_modules.dicta-il.dictalm-7b.c233431901e34e82235e058ff75053a292547e79.modeling_megatron_gpt.MegatronGPTModel",
• "torch._utils._rebuild_parameter",
• "transformers_modules.dicta-il.dictalm-7b.c233431901e34e82235e058ff75053a292547e79.modeling_megatron_gpt.MegatronGPTRotaryEmbedding",
• "transformers.activations.GELUActivation",
• "quanto.nn.qlinear.QLinear",
• "torch.float8_e4m3fn",
• "transformers.generation.configuration_utils.GenerationConfig",
• "quanto.tensor.qtype.qtype"

How to fix it?