=== Dobi Official Validation === Model: /home/xiyaofeng/.cache/huggingface/hub/models--jeffwan--llama-7b-hf/snapshots/82eb0e6908390680598ca3ec1d77adfc5e1b24aa Dobi ratio: 0.6 (= 60% retained) Remapping: False Ground truth: outputs/baselines/dobi_ground_truth/llama7b_remap_r0.6.json Loading model... `torch_dtype` is deprecated! Use `dtype` instead! 2026-04-21 09:37:13.401300: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-04-21 09:37:13.418303: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered WARNING: All log messages before absl::InitializeLog() is called are written to STDERR E0000 00:00:1776764233.436316 2451067 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered E0000 00:00:1776764233.442200 2451067 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered W0000 00:00:1776764233.457554 2451067 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once. W0000 00:00:1776764233.457581 2451067 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once. W0000 00:00:1776764233.457585 2451067 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once. W0000 00:00:1776764233.457587 2451067 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once. 2026-04-21 09:37:13.461722: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. AttributeError: 'MessageFactory' object has no attribute 'GetPrototype' AttributeError: 'MessageFactory' object has no attribute 'GetPrototype' AttributeError: 'MessageFactory' object has no attribute 'GetPrototype' AttributeError: 'MessageFactory' object has no attribute 'GetPrototype' AttributeError: 'MessageFactory' object has no attribute 'GetPrototype' Loading checkpoint shards: 0%| | 0/2 [00:00