developer_uid: Luna1040
submission_id: ilyagusev-saiga-nemo-12b_v26
model_name: ilyagusev-saiga-nemo-12b_v26
model_group: IlyaGusev/saiga_nemo_12b
status: torndown
timestamp: 2025-07-01T14:53:49+00:00
num_battles: 6425
num_wins: 2667
celo_rating: 1223.84
family_friendly_score: 0.6564
family_friendly_standard_error: 0.006716234659390632
submission_type: basic
model_repo: IlyaGusev/saiga_nemo_12b
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5923272930505835, 'latency_mean': 1.6880796885490417, 'latency_p50': 1.689056158065796, 'latency_p90': 1.8535332918167113}, {'batch_size': 3, 'throughput': 1.0649121571574145, 'latency_mean': 2.80676225066185, 'latency_p50': 2.7844852209091187, 'latency_p90': 3.120729374885559}, {'batch_size': 5, 'throughput': 1.2872920984232283, 'latency_mean': 3.8695694172382353, 'latency_p50': 3.8548654317855835, 'latency_p90': 4.2773885965347285}, {'batch_size': 6, 'throughput': 1.3422989696030667, 'latency_mean': 4.45149312376976, 'latency_p50': 4.428252816200256, 'latency_p90': 5.018871450424195}, {'batch_size': 8, 'throughput': 1.406730780287377, 'latency_mean': 5.6545115351676944, 'latency_p50': 5.659544110298157, 'latency_p90': 6.3523108959198}, {'batch_size': 10, 'throughput': 1.4314413193915456, 'latency_mean': 6.918579366207123, 'latency_p50': 6.970006942749023, 'latency_p90': 7.8515613079071045}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: ilyagusev-saiga-nemo-12b_v26
is_internal_developer: False
language_model: IlyaGusev/saiga_nemo_12b
model_size: 13B
ranking_group: single
throughput_3p7s: 1.27
us_pacific_date: 2025-07-01
win_ratio: 0.4150972762645914
generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 150, 'presence_penalty': 0.7, 'frequency_penalty': 0.7, 'stopping_words': ['|im_end|', '<|eot_id|>', '[/INST]', '[INST]', '<|start_header_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 ilyagusev-saiga-nemo-12b-v26-mkmlizer
Waiting for job on ilyagusev-saiga-nemo-12b-v26-mkmlizer to finish
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ Version: 0.29.3 ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ https://mk1.ai ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ The license key for the current software has been verified as ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ belonging to: ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ Chai Research Corp. ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ║ ║
ilyagusev-saiga-nemo-12b-v26-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
ilyagusev-saiga-nemo-12b-v26-mkmlizer: Downloaded to shared memory in 33.568s
ilyagusev-saiga-nemo-12b-v26-mkmlizer: Checking if IlyaGusev/saiga_nemo_12b already exists in ChaiML
ilyagusev-saiga-nemo-12b-v26-mkmlizer: Creating repo ChaiML/saiga_nemo_12b and uploading /tmp/tmpgmyj01hm to it
ilyagusev-saiga-nemo-12b-v26-mkmlizer: 0%| | 0/6 [00:00<?, ?it/s] 17%|█▋ | 1/6 [00:04<00:21, 4.30s/it] 33%|███▎ | 2/6 [00:08<00:17, 4.26s/it] 50%|█████ | 3/6 [00:12<00:12, 4.33s/it] 67%|██████▋ | 4/6 [00:21<00:11, 5.88s/it] 83%|████████▎ | 5/6 [00:29<00:06, 6.72s/it] 100%|██████████| 6/6 [00:30<00:00, 4.91s/it] 100%|██████████| 6/6 [00:30<00:00, 5.13s/it]
ilyagusev-saiga-nemo-12b-v26-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgmyj01hm, device:0
ilyagusev-saiga-nemo-12b-v26-mkmlizer: Saving flywheel model at /dev/shm/model_cache
ilyagusev-saiga-nemo-12b-v26-mkmlizer: quantized model in 30.519s
ilyagusev-saiga-nemo-12b-v26-mkmlizer: Processed model IlyaGusev/saiga_nemo_12b in 121.168s
ilyagusev-saiga-nemo-12b-v26-mkmlizer: creating bucket guanaco-mkml-models
ilyagusev-saiga-nemo-12b-v26-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
ilyagusev-saiga-nemo-12b-v26-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v26
ilyagusev-saiga-nemo-12b-v26-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v26/special_tokens_map.json
ilyagusev-saiga-nemo-12b-v26-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v26/config.json
ilyagusev-saiga-nemo-12b-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v26/tokenizer_config.json
ilyagusev-saiga-nemo-12b-v26-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v26/tokenizer.json
ilyagusev-saiga-nemo-12b-v26-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/ilyagusev-saiga-nemo-12b-v26/flywheel_model.0.safetensors
ilyagusev-saiga-nemo-12b-v26-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 32.25it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 50.75it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 44.96it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 43.88it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 49.73it/s] Loading 0: 10%|█ | 37/363 [00:00<00:07, 45.78it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.60it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 49.20it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 45.98it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.15it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:08, 33.46it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 39.82it/s] Loading 0: 21%|██ | 77/363 [00:01<00:06, 41.70it/s] Loading 0: 23%|██▎ | 82/363 [00:02<00:08, 34.92it/s] Loading 0: 25%|██▍ | 89/363 [00:02<00:06, 41.93it/s] Loading 0: 26%|██▌ | 94/363 [00:02<00:06, 42.36it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:06, 42.85it/s] Loading 0: 29%|██▊ | 104/363 [00:02<00:05, 44.60it/s] Loading 0: 30%|███ | 110/363 [00:02<00:05, 42.51it/s] Loading 0: 32%|███▏ | 115/363 [00:02<00:05, 43.31it/s] Loading 0: 33%|███▎ | 120/363 [00:02<00:05, 41.16it/s] Loading 0: 34%|███▍ | 125/363 [00:02<00:05, 43.02it/s] Loading 0: 36%|███▌ | 130/363 [00:03<00:05, 42.95it/s] Loading 0: 37%|███▋ | 135/363 [00:03<00:05, 43.05it/s] Loading 0: 39%|███▉ | 141/363 [00:03<00:05, 40.63it/s] Loading 0: 40%|████ | 146/363 [00:03<00:07, 28.83it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:07, 29.23it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:06, 34.05it/s] Loading 0: 44%|████▍ | 160/363 [00:04<00:05, 34.50it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 38.11it/s] Loading 0: 47%|████▋ | 170/363 [00:04<00:04, 38.91it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 37.85it/s] Loading 0: 49%|████▉ | 179/363 [00:04<00:04, 37.53it/s] Loading 0: 50%|█████ | 183/363 [00:04<00:04, 37.83it/s] Loading 0: 52%|█████▏ | 187/363 [00:04<00:04, 37.23it/s] Loading 0: 53%|█████▎ | 192/363 [00:04<00:04, 39.39it/s] Loading 0: 54%|█████▍ | 196/363 [00:04<00:04, 38.89it/s] Loading 0: 55%|█████▌ | 201/363 [00:05<00:03, 41.86it/s] Loading 0: 57%|█████▋ | 206/363 [00:05<00:03, 42.04it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 42.05it/s] Loading 0: 60%|█████▉ | 217/363 [00:05<00:03, 40.49it/s] Loading 0: 61%|██████ | 222/363 [00:05<00:03, 42.59it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 28.41it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 29.01it/s] Loading 0: 65%|██████▌ | 237/363 [00:06<00:03, 34.29it/s] Loading 0: 66%|██████▋ | 241/363 [00:06<00:03, 34.26it/s] Loading 0: 68%|██████▊ | 246/363 [00:06<00:03, 37.75it/s] Loading 0: 69%|██████▉ | 251/363 [00:06<00:02, 39.25it/s] Loading 0: 71%|███████ | 256/363 [00:06<00:02, 40.41it/s] Loading 0: 72%|███████▏ | 261/363 [00:06<00:02, 42.56it/s] Loading 0: 73%|███████▎ | 266/363 [00:06<00:02, 36.05it/s] Loading 0: 75%|███████▌ | 273/363 [00:06<00:02, 43.36it/s] Loading 0: 77%|███████▋ | 278/363 [00:07<00:01, 43.09it/s] Loading 0: 78%|███████▊ | 283/363 [00:07<00:01, 42.22it/s] Loading 0: 79%|███████▉ | 288/363 [00:07<00:01, 43.81it/s] Loading 0: 81%|████████ | 293/363 [00:07<00:01, 36.85it/s] Loading 0: 82%|████████▏ | 299/363 [00:07<00:01, 40.75it/s] Loading 0: 84%|████████▎ | 304/363 [00:08<00:02, 22.90it/s] Loading 0: 85%|████████▍ | 308/363 [00:08<00:02, 25.30it/s] Loading 0: 86%|████████▌ | 312/363 [00:08<00:01, 25.72it/s] Loading 0: 88%|████████▊ | 320/363 [00:08<00:01, 35.06it/s] Loading 0: 90%|████████▉ | 326/363 [00:08<00:01, 35.87it/s] Loading 0: 91%|█████████ | 331/363 [00:08<00:00, 36.76it/s] Loading 0: 93%|█████████▎| 337/363 [00:08<00:00, 41.41it/s] Loading 0: 94%|█████████▍| 342/363 [00:08<00:00, 41.28it/s] Loading 0: 96%|█████████▌| 347/363 [00:09<00:00, 41.57it/s] Loading 0: 97%|█████████▋| 353/363 [00:09<00:00, 40.10it/s] Loading 0: 99%|█████████▊| 358/363 [00:09<00:00, 40.44it/s]
Job ilyagusev-saiga-nemo-12b-v26-mkmlizer completed after 145.82s with status: succeeded
Stopping job with name ilyagusev-saiga-nemo-12b-v26-mkmlizer
Pipeline stage MKMLizer completed in 146.56s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service ilyagusev-saiga-nemo-12b-v26
Waiting for inference service ilyagusev-saiga-nemo-12b-v26 to be ready
Failed to get response for submission chaiml-mistralnemo-12b-_88791_v2: HTTPConnectionPool(host='chaiml-mistralnemo-12b-88791-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service ilyagusev-saiga-nemo-12b-v26 ready after 211.36425805091858s
Pipeline stage MKMLDeployer completed in 211.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.621483564376831s
Received healthy response to inference request in 1.7459092140197754s
Received healthy response to inference request in 1.713836908340454s
Received healthy response to inference request in 1.767439603805542s
Received healthy response to inference request in 2.0448710918426514s
5 requests
0 failed requests
5th percentile: 1.7202513694763184
10th percentile: 1.7266658306121827
20th percentile: 1.739494752883911
30th percentile: 1.7502152919769287
40th percentile: 1.7588274478912354
50th percentile: 1.767439603805542
60th percentile: 1.8784121990203857
70th percentile: 1.9893847942352294
80th percentile: 2.160193586349487
90th percentile: 2.3908385753631594
95th percentile: 2.506161069869995
99th percentile: 2.598419065475464
mean time: 1.9787080764770508
Pipeline stage StressChecker completed in 11.25s
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 1.65s
Shutdown handler de-registered
ilyagusev-saiga-nemo-12b_v26 status is now deployed due to DeploymentManager action
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 3194.13s
Shutdown handler de-registered
ilyagusev-saiga-nemo-12b_v26 status is now inactive due to auto deactivation removed underperforming models
ilyagusev-saiga-nemo-12b_v26 status is now torndown due to DeploymentManager action