vikhrmodels-vikhr-nemo-_15342

developer_uid: zmeeks

submission_id: vikhrmodels-vikhr-nemo-_15342_v2

model_name: w1000

model_group: Vikhrmodels/Vikhr-Nemo-1

status: torndown

timestamp: 2025-06-28T09:41:10+00:00

num_battles: 6554

num_wins: 2599

celo_rating: 1197.35

family_friendly_score: 0.7572

family_friendly_standard_error: 0.006063796830369566

submission_type: basic

model_repo: Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24

model_architecture: MistralForCausalLM

model_num_parameters: 12772090880.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5912462068601096, 'latency_mean': 1.6912438130378724, 'latency_p50': 1.6975831985473633, 'latency_p90': 1.8664578914642334}, {'batch_size': 3, 'throughput': 1.0846430987071718, 'latency_mean': 2.7561889719963073, 'latency_p50': 2.7421170473098755, 'latency_p90': 3.0555963277816773}, {'batch_size': 5, 'throughput': 1.303779427998507, 'latency_mean': 3.813551789522171, 'latency_p50': 3.8115473985671997, 'latency_p90': 4.264092946052551}, {'batch_size': 6, 'throughput': 1.3485524289101136, 'latency_mean': 4.4244551336765285, 'latency_p50': 4.452584266662598, 'latency_p90': 4.909177231788635}, {'batch_size': 8, 'throughput': 1.4221544833576534, 'latency_mean': 5.585198667049408, 'latency_p50': 5.606345057487488, 'latency_p90': 6.233723092079162}, {'batch_size': 10, 'throughput': 1.451483095639202, 'latency_mean': 6.829037024974823, 'latency_p50': 6.813153505325317, 'latency_p90': 7.650868606567383}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: w1000

is_internal_developer: False

language_model: Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-06-28

win_ratio: 0.39655172413793105

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '### Instruction:\n{memory}\n', 'prompt_template': '### Input:\n{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', '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 vikhrmodels-vikhr-nemo-15342-v2-mkmlizer
Waiting for job on vikhrmodels-vikhr-nemo-15342-v2-mkmlizer to finish
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║                                                                     ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║                                                                     ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  https://mk1.ai                                                     ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║                                                                     ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  belonging to:                                                      ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║                                                                     ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  Chai Research Corp.                                                ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ║                                                                     ║
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Downloaded to shared memory in 52.600s
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Checking if Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24 already exists in ChaiML
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Creating repo ChaiML/Vikhr-Nemo-12B-Instruct-R-21-09-24 and uploading /tmp/tmpqwc288u6 to it
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:04<00:22,  4.55s/it]
 33%|███▎      | 2/6 [00:10<00:22,  5.54s/it]
 50%|█████     | 3/6 [00:14<00:13,  4.64s/it]
 67%|██████▋   | 4/6 [00:17<00:08,  4.20s/it]
 83%|████████▎ | 5/6 [00:21<00:04,  4.04s/it]
100%|██████████| 6/6 [00:24<00:00,  3.62s/it]
100%|██████████| 6/6 [00:24<00:00,  4.07s/it]
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqwc288u6, device:0
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: quantized model in 29.567s
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Processed model Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24 in 136.368s
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: creating bucket guanaco-mkml-models
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/vikhrmodels-vikhr-nemo-15342-v2
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/vikhrmodels-vikhr-nemo-15342-v2/config.json
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/vikhrmodels-vikhr-nemo-15342-v2/special_tokens_map.json
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/vikhrmodels-vikhr-nemo-15342-v2/tokenizer_config.json
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/vikhrmodels-vikhr-nemo-15342-v2/tokenizer.json
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/vikhrmodels-vikhr-nemo-15342-v2/flywheel_model.0.safetensors
vikhrmodels-vikhr-nemo-15342-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.76it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.50it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 46.51it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.20it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.27it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.77it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 46.97it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.66it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.96it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.72it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.11it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.19it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 40.02it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 38.62it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.79it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 44.73it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 38.89it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 48.42it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 44.83it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 43.35it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 46.71it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:05, 46.57it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 46.78it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 44.96it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.27it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.32it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.60it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 38.68it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 40.92it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 41.45it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.73it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 46.06it/s]
Loading 0:  52%|█████▏    | 189/363 [00:04<00:03, 44.95it/s]
Loading 0:  53%|█████▎    | 194/363 [00:04<00:04, 39.25it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 47.43it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:03, 45.61it/s]
Loading 0:  59%|█████▊    | 213/363 [00:04<00:03, 44.73it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:02, 48.27it/s]
Loading 0:  62%|██████▏   | 224/363 [00:05<00:04, 34.17it/s]
Loading 0:  63%|██████▎   | 229/363 [00:05<00:03, 34.52it/s]
Loading 0:  65%|██████▍   | 235/363 [00:05<00:03, 36.30it/s]
Loading 0:  66%|██████▌   | 239/363 [00:05<00:03, 34.99it/s]
Loading 0:  68%|██████▊   | 246/363 [00:05<00:02, 41.53it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 40.85it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 41.17it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 43.21it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 37.70it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:01, 46.30it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 45.05it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 43.66it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 47.92it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 45.99it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 26.09it/s]
Loading 0:  85%|████████▍ | 308/363 [00:07<00:01, 27.77it/s]
Loading 0:  86%|████████▌ | 312/363 [00:07<00:01, 26.38it/s]
Loading 0:  88%|████████▊ | 320/363 [00:07<00:01, 35.45it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:00, 37.25it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 38.58it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 43.96it/s]
Loading 0:  95%|█████████▍| 344/363 [00:08<00:00, 43.54it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 43.26it/s]
Loading 0:  98%|█████████▊| 356/363 [00:08<00:00, 47.57it/s]
Loading 0: 100%|█████████▉| 362/363 [00:08<00:00, 45.89it/s]
                                                            
Job vikhrmodels-vikhr-nemo-15342-v2-mkmlizer completed after 167.44s with status: succeeded
Stopping job with name vikhrmodels-vikhr-nemo-15342-v2-mkmlizer
Pipeline stage MKMLizer completed in 168.26s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service vikhrmodels-vikhr-nemo-15342-v2
Waiting for inference service vikhrmodels-vikhr-nemo-15342-v2 to be ready
Inference service vikhrmodels-vikhr-nemo-15342-v2 ready after 160.57981967926025s
Pipeline stage MKMLDeployer completed in 161.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.174264430999756s
Received healthy response to inference request in 1.4502854347229004s
Received healthy response to inference request in 1.6816120147705078s
Received healthy response to inference request in 1.635465383529663s
Received healthy response to inference request in 1.5936739444732666s
5 requests
0 failed requests
5th percentile: 1.4789631366729736
10th percentile: 1.5076408386230469
20th percentile: 1.5649962425231934
30th percentile: 1.602032232284546
40th percentile: 1.6187488079071044
50th percentile: 1.635465383529663
60th percentile: 1.653924036026001
70th percentile: 1.672382688522339
80th percentile: 1.7801424980163576
90th percentile: 1.9772034645080567
95th percentile: 2.075733947753906
99th percentile: 2.154558334350586
mean time: 1.7070602416992187
Pipeline stage StressChecker completed in 10.05s
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 0.91s
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 0.69s
Shutdown handler de-registered
vikhrmodels-vikhr-nemo-_15342_v2 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service vikhrmodels-vikhr-nemo-15342-v2-profiler
Waiting for inference service vikhrmodels-vikhr-nemo-15342-v2-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 3005.54s
Shutdown handler de-registered
vikhrmodels-vikhr-nemo-_15342_v2 status is now inactive due to auto deactivation removed underperforming models
vikhrmodels-vikhr-nemo-_15342_v2 status is now torndown due to DeploymentManager action