developer_uid: NischayDnk
submission_id: delta-vector-hamanasu-q_63301_v1
model_name: delta-vector-hamanasu-q_63301_v1
model_group: Delta-Vector/Hamanasu-Qw
status: torndown
timestamp: 2025-05-13T14:27:44+00:00
num_battles: 12936
num_wins: 6127
celo_rating: 1263.82
family_friendly_score: 0.583
family_friendly_standard_error: 0.006972962067873307
submission_type: basic
model_repo: Delta-Vector/Hamanasu-QwQ-V2-RP
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3846814417846688, 'latency_mean': 2.5994867503643038, 'latency_p50': 2.5957618951797485, 'latency_p90': 2.8899114847183225}, {'batch_size': 3, 'throughput': 0.8755158541673818, 'latency_mean': 3.4248341131210327, 'latency_p50': 3.3786877393722534, 'latency_p90': 3.8406206607818603}, {'batch_size': 5, 'throughput': 1.1878564931670046, 'latency_mean': 4.185281652212143, 'latency_p50': 4.191197633743286, 'latency_p90': 4.681160902976989}, {'batch_size': 6, 'throughput': 1.2976181783637706, 'latency_mean': 4.600130419731141, 'latency_p50': 4.588589310646057, 'latency_p90': 5.138482666015625}, {'batch_size': 8, 'throughput': 1.4611719995677837, 'latency_mean': 5.4144472098350525, 'latency_p50': 5.455518007278442, 'latency_p90': 6.127187371253967}, {'batch_size': 10, 'throughput': 1.5980679364500618, 'latency_mean': 6.190765601396561, 'latency_p50': 6.128163456916809, 'latency_p90': 7.042241096496582}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: delta-vector-hamanasu-q_63301_v1
is_internal_developer: False
language_model: Delta-Vector/Hamanasu-QwQ-V2-RP
model_size: 33B
ranking_group: single
throughput_3p7s: 1.01
us_pacific_date: 2025-05-13
win_ratio: 0.4736394557823129
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['\n', '<|im_end|>', '<|im_start|>'], 'max_input_tokens': 768, 'best_of': 5, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name delta-vector-hamanasu-q-63301-v1-mkmlizer
Waiting for job on delta-vector-hamanasu-q-63301-v1-mkmlizer to finish
delta-vector-hamanasu-q-63301-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║     _____            __           __                                ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║       /___/                                                         ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║                                                                     ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║  https://mk1.ai                                                     ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║                                                                     ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║  belonging to:                                                      ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║                                                                     ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║  Chai Research Corp.                                                ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ║                                                                     ║
delta-vector-hamanasu-q-63301-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
delta-vector-hamanasu-q-63301-v1-mkmlizer: Downloaded to shared memory in 127.229s
delta-vector-hamanasu-q-63301-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9p733egf, device:0
delta-vector-hamanasu-q-63301-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
delta-vector-hamanasu-q-63301-v1-mkmlizer: quantized model in 63.363s
delta-vector-hamanasu-q-63301-v1-mkmlizer: Processed model Delta-Vector/Hamanasu-QwQ-V2-RP in 190.592s
delta-vector-hamanasu-q-63301-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
delta-vector-hamanasu-q-63301-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1
delta-vector-hamanasu-q-63301-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1/config.json
delta-vector-hamanasu-q-63301-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1/added_tokens.json
delta-vector-hamanasu-q-63301-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1/special_tokens_map.json
delta-vector-hamanasu-q-63301-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1/tokenizer_config.json
delta-vector-hamanasu-q-63301-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1/merges.txt
delta-vector-hamanasu-q-63301-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1/vocab.json
delta-vector-hamanasu-q-63301-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1/tokenizer.json
delta-vector-hamanasu-q-63301-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1/flywheel_model.2.safetensors
delta-vector-hamanasu-q-63301-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1/flywheel_model.1.safetensors
delta-vector-hamanasu-q-63301-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/delta-vector-hamanasu-q-63301-v1/flywheel_model.0.safetensors
delta-vector-hamanasu-q-63301-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:18, 41.24it/s]
Loading 0:   2%|▏         | 17/771 [00:00<00:10, 69.18it/s]
Loading 0:   4%|▍         | 29/771 [00:00<00:09, 77.23it/s]
Loading 0:   6%|▌         | 46/771 [00:00<00:11, 65.29it/s]
Loading 0:   7%|▋         | 53/771 [00:00<00:13, 54.31it/s]
Loading 0:   8%|▊         | 64/771 [00:01<00:10, 65.30it/s]
Loading 0:  10%|▉         | 75/771 [00:01<00:09, 75.13it/s]
Loading 0:  11%|█▏        | 87/771 [00:01<00:08, 79.54it/s]
Loading 0:  13%|█▎        | 98/771 [00:01<00:08, 80.16it/s]
Loading 0:  14%|█▍        | 107/771 [00:01<00:10, 61.02it/s]
Loading 0:  15%|█▍        | 115/771 [00:01<00:10, 64.85it/s]
Loading 0:  16%|█▌        | 123/771 [00:01<00:11, 57.96it/s]
Loading 0:  17%|█▋        | 133/771 [00:02<00:10, 61.88it/s]
Loading 0:  20%|█▉        | 151/771 [00:02<00:07, 84.40it/s]
Loading 0:  21%|██        | 161/771 [00:02<00:08, 75.26it/s]
Loading 0:  22%|██▏       | 170/771 [00:02<00:10, 55.29it/s]
Loading 0:  23%|██▎       | 177/771 [00:02<00:10, 55.03it/s]
Loading 0:  24%|██▍       | 185/771 [00:02<00:10, 56.69it/s]
Loading 0:  25%|██▌       | 196/771 [00:02<00:08, 67.85it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:07, 77.58it/s]
Loading 0:  28%|██▊       | 218/771 [00:03<00:07, 78.15it/s]
Loading 0:  29%|██▉       | 227/771 [00:03<00:09, 59.80it/s]
Loading 0:  30%|███       | 235/771 [00:03<00:09, 56.35it/s]
Loading 0:  32%|███▏      | 245/771 [00:03<00:08, 61.34it/s]
Loading 0:  33%|███▎      | 257/771 [00:03<00:07, 69.05it/s]
Loading 0:  35%|███▍      | 269/771 [00:04<00:06, 74.33it/s]
Loading 0:  37%|███▋      | 286/771 [00:04<00:06, 71.24it/s]
Loading 0:  38%|███▊      | 294/771 [00:04<00:07, 60.53it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:19,  2.35it/s]
Loading 0:  41%|████      | 315/771 [00:19<02:12,  3.45it/s]
Loading 0:  42%|████▏     | 327/771 [00:19<01:29,  4.97it/s]
Loading 0:  44%|████▍     | 338/771 [00:19<01:03,  6.86it/s]
Loading 0:  45%|████▍     | 346/771 [00:19<00:50,  8.47it/s]
Loading 0:  46%|████▌     | 353/771 [00:20<00:42,  9.84it/s]
Loading 0:  47%|████▋     | 365/771 [00:20<00:28, 14.40it/s]
Loading 0:  49%|████▉     | 376/771 [00:20<00:19, 19.91it/s]
Loading 0:  50%|█████     | 388/771 [00:20<00:14, 26.78it/s]
Loading 0:  52%|█████▏    | 399/771 [00:20<00:10, 34.71it/s]
Loading 0:  53%|█████▎    | 408/771 [00:20<00:10, 33.36it/s]
Loading 0:  54%|█████▍    | 416/771 [00:20<00:09, 37.96it/s]
Loading 0:  55%|█████▌    | 425/771 [00:21<00:07, 43.42it/s]
Loading 0:  57%|█████▋    | 436/771 [00:21<00:06, 54.36it/s]
Loading 0:  58%|█████▊    | 448/771 [00:21<00:05, 62.66it/s]
Loading 0:  60%|█████▉    | 459/771 [00:21<00:04, 72.13it/s]
Loading 0:  61%|██████    | 469/771 [00:21<00:05, 55.48it/s]
Loading 0:  62%|██████▏   | 477/771 [00:21<00:05, 56.94it/s]
Loading 0:  63%|██████▎   | 485/771 [00:21<00:04, 58.70it/s]
Loading 0:  64%|██████▍   | 497/771 [00:22<00:04, 66.32it/s]
Loading 0:  66%|██████▌   | 509/771 [00:22<00:03, 71.98it/s]
Loading 0:  68%|██████▊   | 526/771 [00:22<00:03, 69.79it/s]
Loading 0:  69%|██████▉   | 534/771 [00:22<00:03, 60.15it/s]
Loading 0:  71%|███████   | 545/771 [00:22<00:03, 65.17it/s]
Loading 0:  72%|███████▏  | 556/771 [00:22<00:02, 73.85it/s]
Loading 0:  74%|███████▎  | 568/771 [00:23<00:02, 77.89it/s]
Loading 0:  75%|███████▍  | 578/771 [00:23<00:02, 81.43it/s]
Loading 0:  76%|███████▌  | 587/771 [00:23<00:03, 61.10it/s]
Loading 0:  77%|███████▋  | 595/771 [00:23<00:03, 57.73it/s]
Loading 0:  78%|███████▊  | 605/771 [00:23<00:02, 62.65it/s]
Loading 0:  80%|████████  | 617/771 [00:23<00:02, 69.90it/s]
Loading 0:  81%|████████▏ | 627/771 [00:38<01:02,  2.32it/s]
Loading 0:  83%|████████▎ | 638/771 [00:38<00:39,  3.34it/s]
Loading 0:  84%|████████▍ | 646/771 [00:38<00:28,  4.31it/s]
Loading 0:  85%|████████▍ | 653/771 [00:38<00:22,  5.29it/s]
Loading 0:  86%|████████▋ | 665/771 [00:39<00:13,  8.08it/s]
Loading 0:  88%|████████▊ | 677/771 [00:39<00:08, 11.75it/s]
Loading 0:  89%|████████▉ | 689/771 [00:39<00:04, 16.45it/s]
Loading 0:  92%|█████████▏| 706/771 [00:39<00:02, 23.73it/s]
Loading 0:  93%|█████████▎| 714/771 [00:39<00:02, 26.01it/s]
Loading 0:  94%|█████████▍| 725/771 [00:39<00:01, 32.71it/s]
Loading 0:  96%|█████████▌| 737/771 [00:40<00:00, 40.89it/s]
Loading 0:  97%|█████████▋| 749/771 [00:40<00:00, 49.10it/s]
Loading 0:  99%|█████████▉| 766/771 [00:47<00:00,  5.31it/s]
                                                            

Job delta-vector-hamanasu-q-63301-v1-mkmlizer completed after 219.35s with status: succeeded
Stopping job with name delta-vector-hamanasu-q-63301-v1-mkmlizer
Pipeline stage MKMLizer completed in 219.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service delta-vector-hamanasu-q-63301-v1
Waiting for inference service delta-vector-hamanasu-q-63301-v1 to be ready
Inference service delta-vector-hamanasu-q-63301-v1 ready after 130.4577603340149s
Pipeline stage MKMLDeployer completed in 131.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2628772258758545s
Received healthy response to inference request in 2.1873905658721924s
Received healthy response to inference request in 2.3335816860198975s
Received healthy response to inference request in 2.7003285884857178s
Received healthy response to inference request in 2.0222582817077637s
5 requests
0 failed requests
5th percentile: 2.0552847385406494
10th percentile: 2.088311195373535
20th percentile: 2.1543641090393066
30th percentile: 2.202487897872925
40th percentile: 2.2326825618743897
50th percentile: 2.2628772258758545
60th percentile: 2.2911590099334718
70th percentile: 2.319440793991089
80th percentile: 2.4069310665130614
90th percentile: 2.55362982749939
95th percentile: 2.626979207992554
99th percentile: 2.685658712387085
mean time: 2.3012872695922852
Pipeline stage StressChecker completed in 13.06s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.74s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.83s
Shutdown handler de-registered
delta-vector-hamanasu-q_63301_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service delta-vector-hamanasu-q-63301-v1-profiler
Waiting for inference service delta-vector-hamanasu-q-63301-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3142.61s
Shutdown handler de-registered
delta-vector-hamanasu-q_63301_v1 status is now inactive due to auto deactivation removed underperforming models
delta-vector-hamanasu-q_63301_v1 status is now torndown due to DeploymentManager action