GGUF
conversational
Experiment_1 / opt /verify2_ab.jsonl
HelloSun's picture
Upload opt/verify2_ab.jsonl with huggingface_hub
18f561f verified
Raw History Blame Contribute Delete
13 kB
{"label":"stock_r1","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T04:54:20Z", "avg_ns": 2242675802, "stddev_ns": 25840206, "avg_ts": 228.318853, "stddev_ts": 2.621886, "samples_ns": [ 2219913236, 2237350336, 2270763834 ],"samples_ts": [ 230.64, 228.842, 225.475 ]}
{"label":"stock_r1","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 128, "n_depth": 0, "test_time": "2026-10-27T04:54:29Z", "avg_ns": 8452155224, "stddev_ns": 108936643, "avg_ts": 15.145756, "stddev_ts": 0.196623, "samples_ns": [ 8505389346, 8524238662, 8326837664 ],"samples_ts": [ 15.0493, 15.016, 15.372 ]}
{"label":"vnni_r1","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T04:54:55Z", "avg_ns": 2262109527, "stddev_ns": 19988866, "avg_ts": 226.349243, "stddev_ts": 2.009611, "samples_ns": [ 2276111728, 2239218051, 2270998804 ],"samples_ts": [ 224.945, 228.651, 225.451 ]}
{"label":"vnni_r1","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 128, "n_depth": 0, "test_time": "2026-10-27T04:55:04Z", "avg_ns": 5921683904, "stddev_ns": 308937725, "avg_ts": 21.653689, "stddev_ts": 1.098844, "samples_ns": [ 5708067725, 5781068049, 6275915939 ],"samples_ts": [ 22.4244, 22.1412, 20.3954 ]}
{"label":"stock_r2","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T04:55:22Z", "avg_ns": 2268893575, "stddev_ns": 43065975, "avg_ts": 225.715458, "stddev_ts": 4.331227, "samples_ns": [ 2219231945, 2291495016, 2295953764 ],"samples_ts": [ 230.71, 223.435, 223.001 ]}
{"label":"stock_r2","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 128, "n_depth": 0, "test_time": "2026-10-27T04:55:31Z", "avg_ns": 8400335076, "stddev_ns": 188997177, "avg_ts": 15.242668, "stddev_ts": 0.345425, "samples_ns": [ 8194126352, 8441565334, 8565313542 ],"samples_ts": [ 15.6209, 15.1631, 14.944 ]}
{"label":"vnni_r2","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T04:55:57Z", "avg_ns": 2267069843, "stddev_ns": 33138473, "avg_ts": 225.874602, "stddev_ts": 3.326892, "samples_ns": [ 2280907655, 2291046571, 2229255305 ],"samples_ts": [ 224.472, 223.479, 229.673 ]}
{"label":"vnni_r2","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 128, "n_depth": 0, "test_time": "2026-10-27T04:56:06Z", "avg_ns": 5691579525, "stddev_ns": 45728591, "avg_ts": 22.490332, "stddev_ts": 0.180861, "samples_ns": [ 5735545149, 5644271502, 5694921925 ],"samples_ts": [ 22.317, 22.6779, 22.4762 ]}
{"label":"stock_r3","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T04:56:23Z", "avg_ns": 2239697375, "stddev_ns": 23435243, "avg_ts": 228.619100, "stddev_ts": 2.406456, "samples_ns": [ 2251724366, 2254677313, 2212690446 ],"samples_ts": [ 227.381, 227.083, 231.393 ]}
{"label":"stock_r3","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 128, "n_depth": 0, "test_time": "2026-10-27T04:56:32Z", "avg_ns": 8333136097, "stddev_ns": 91272023, "avg_ts": 15.361596, "stddev_ts": 0.168827, "samples_ns": [ 8233683318, 8413068985, 8352655989 ],"samples_ts": [ 15.5459, 15.2144, 15.3245 ]}
{"label":"vnni_r3","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 512, "n_gen": 0, "n_depth": 0, "test_time": "2026-10-27T04:56:58Z", "avg_ns": 2268640794, "stddev_ns": 40390373, "avg_ts": 225.733282, "stddev_ts": 4.001125, "samples_ns": [ 2232293415, 2261505816, 2312123153 ],"samples_ts": [ 229.361, 226.398, 221.441 ]}
{"label":"vnni_r3","build_commit": "1268edac5", "build_number": 1, "cpu_info": "Intel(R) Xeon(R) Platinum 8559C", "gpu_info": "", "backends": "CPU", "model_filename": "/root/app/verify2/openpangu-vl-artifacts/openPangu-VL-7B-Q4_K_M.gguf", "model_type": "pangu_vl 7B Q4_K - Medium", "model_size": 4929676288, "model_n_params": 8030887936, "n_batch": 2048, "n_ubatch": 512, "n_threads": 16, "cpu_mask": "0x0", "cpu_strict": false, "poll": 50, "type_k": "f16", "type_v": "f16", "n_gpu_layers": -1, "n_cpu_moe": 0, "split_mode": "layer", "main_gpu": 0, "no_kv_offload": false, "flash_attn": 1, "devices": "auto", "tensor_split": "0.00", "tensor_buft_overrides": "none", "load_mode": "auto", "lazy_mode": "auto", "embeddings": false, "no_op_offload": 0, "no_host": false, "repack": false, "fit_target": 0, "fit_min_ctx": 0, "n_prompt": 0, "n_gen": 128, "n_depth": 0, "test_time": "2026-10-27T04:57:07Z", "avg_ns": 5940173953, "stddev_ns": 95706391, "avg_ts": 21.551892, "stddev_ts": 0.344576, "samples_ns": [ 6048604774, 5904445549, 5867471538 ],"samples_ts": [ 21.1619, 21.6786, 21.8152 ]}