developer_uid: junhua024
submission_id: junhua024-chai-16-full-qkv_72_v3
model_name: junhua024-chai-16-full-qkv_72_v3
model_group: junhua024/chai_16_full_q
status: torndown
timestamp: 2025-07-20T15:27:44+00:00
num_battles: 8598
num_wins: 4198
celo_rating: 1279.68
family_friendly_score: 0.5558000000000001
family_friendly_standard_error: 0.0070268963276826565
submission_type: basic
model_repo: junhua024/chai_16_full_qkv100_o106_ffn106_1624
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': 0.5949306287903237, 'latency_mean': 1.6807624661922456, 'latency_p50': 1.6720691919326782, 'latency_p90': 1.8627524375915527}, {'batch_size': 3, 'throughput': 1.059301527273159, 'latency_mean': 2.8210466599464414, 'latency_p50': 2.8232632875442505, 'latency_p90': 3.068858814239502}, {'batch_size': 5, 'throughput': 1.258451348001644, 'latency_mean': 3.9439592969417574, 'latency_p50': 3.9402002096176147, 'latency_p90': 4.543553400039673}, {'batch_size': 6, 'throughput': 1.324833333579708, 'latency_mean': 4.506761329174042, 'latency_p50': 4.504460453987122, 'latency_p90': 4.996414375305176}, {'batch_size': 8, 'throughput': 1.37722178570765, 'latency_mean': 5.771358428001403, 'latency_p50': 5.772402763366699, 'latency_p90': 6.49395010471344}, {'batch_size': 10, 'throughput': 1.4079203032808427, 'latency_mean': 7.046059988737106, 'latency_p50': 7.050140380859375, 'latency_p90': 7.939491176605225}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-16-full-qkv_72_v3
is_internal_developer: False
language_model: junhua024/chai_16_full_qkv100_o106_ffn106_1624
model_size: 13B
ranking_group: single
throughput_3p7s: 1.23
us_pacific_date: 2025-07-20
win_ratio: 0.4882530821121191
generation_params: {'temperature': 1.0, 'top_p': 0.88, 'min_p': 0.0, 'top_k': 10, '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': "{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 junhua024-chai-16-full-qkv-72-v3-mkmlizer
Waiting for job on junhua024-chai-16-full-qkv-72-v3-mkmlizer to finish
Failed to get response for submission junhua024-chai-16-full-_94000_v6: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission junhua024-chai-16-full-_94000_v7: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-qkv-72-v3-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`
junhua024-chai-16-full-qkv-72-v3-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`
junhua024-chai-16-full-qkv-72-v3-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`
junhua024-chai-16-full-qkv-72-v3-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`
junhua024-chai-16-full-qkv-72-v3-mkmlizer: Downloaded to shared memory in 81.302s
junhua024-chai-16-full-qkv-72-v3-mkmlizer: Checking if junhua024/chai_16_full_qkv100_o106_ffn106_1624 already exists in ChaiML
junhua024-chai-16-full-qkv-72-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpje_qsje6, device:0
junhua024-chai-16-full-qkv-72-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission junhua024-chai-16-full-_94000_v6: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-qkv-72-v3-mkmlizer: quantized model in 32.223s
junhua024-chai-16-full-qkv-72-v3-mkmlizer: Processed model junhua024/chai_16_full_qkv100_o106_ffn106_1624 in 113.601s
junhua024-chai-16-full-qkv-72-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-qkv-72-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-qkv-72-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v3/nvidia
junhua024-chai-16-full-qkv-72-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v3/nvidia/config.json
junhua024-chai-16-full-qkv-72-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v3/nvidia/special_tokens_map.json
junhua024-chai-16-full-qkv-72-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v3/nvidia/tokenizer_config.json
junhua024-chai-16-full-qkv-72-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v3/nvidia/tokenizer.json
junhua024-chai-16-full-qkv-72-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v3/nvidia/flywheel_model.0.safetensors
junhua024-chai-16-full-qkv-72-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:23, 15.46it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.20it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.91it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 31.69it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.32it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:07, 45.27it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:08, 38.58it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:09, 34.62it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 42.46it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:09, 31.35it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.65it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 36.10it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.91it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 35.08it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 33.16it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 38.04it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 37.43it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:06, 38.66it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 38.61it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:07, 36.03it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:05, 43.22it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.32it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 33.65it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 36.15it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 34.61it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 35.17it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 35.39it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 36.18it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 45.85it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 34.44it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 33.97it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 43.11it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:05, 31.47it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 32.20it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 34.33it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 33.13it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 33.29it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 33.16it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 33.15it/s]
Loading 0:  61%|██████    | 220/363 [00:06<00:03, 42.56it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:04, 33.03it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:03, 34.03it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 40.95it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 34.48it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 32.62it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 34.10it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 32.88it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 34.11it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 34.40it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 35.69it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:01, 46.83it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:01, 37.54it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 36.36it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 40.45it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 34.28it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 33.91it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 35.66it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 34.27it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 34.61it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 34.55it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 35.50it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 44.89it/s]
Loading 0:  97%|█████████▋| 351/363 [00:10<00:00, 24.99it/s]
Loading 0:  98%|█████████▊| 355/363 [00:10<00:00, 27.03it/s]
Loading 0:  99%|█████████▉| 359/363 [00:10<00:00, 28.82it/s]
                                                            

Job junhua024-chai-16-full-qkv-72-v3-mkmlizer completed after 137.41s with status: succeeded
Stopping job with name junhua024-chai-16-full-qkv-72-v3-mkmlizer
Pipeline stage MKMLizer completed in 137.93s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-16-full-qkv-72-v3
Waiting for inference service junhua024-chai-16-full-qkv-72-v3 to be ready
Failed to get response for submission junhua024-chai-16-full-_94000_v6: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_94000_v7: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Retrying (%r) after connection broken by '%r': %s
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_94000_v7: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_94000_v6: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-qkv-72-v3 ready after 331.4738941192627s
Pipeline stage MKMLDeployer completed in 332.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.788382053375244s
Received healthy response to inference request in 1.7348377704620361s
Received healthy response to inference request in 1.915440320968628s
Received healthy response to inference request in 3.668729543685913s
Received healthy response to inference request in 1.7781202793121338s
5 requests
0 failed requests
5th percentile: 1.7434942722320557
10th percentile: 1.7521507740020752
20th percentile: 1.7694637775421143
30th percentile: 1.8055842876434327
40th percentile: 1.8605123043060303
50th percentile: 1.915440320968628
60th percentile: 2.2646170139312742
70th percentile: 2.6137937068939205
80th percentile: 2.964451551437378
90th percentile: 3.3165905475616455
95th percentile: 3.4926600456237793
99th percentile: 3.633515644073486
mean time: 2.377101993560791
Pipeline stage StressChecker completed in 13.14s
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 0.67s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.68s
Shutdown handler de-registered
junhua024-chai-16-full-qkv_72_v3 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4304.91s
Shutdown handler de-registered
junhua024-chai-16-full-qkv_72_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-qkv_72_v3 status is now torndown due to DeploymentManager action