junhua024-chai-16-full-qkv_72

developer_uid: junhua024

submission_id: junhua024-chai-16-full-qkv_72_v2

model_name: junhua024-chai-16-full-qkv_72_v2

model_group: junhua024/chai_16_full_q

status: torndown

timestamp: 2025-07-20T15:26:43+00:00

num_battles: 8464

num_wins: 4192

celo_rating: 1281.19

family_friendly_score: 0.5602

family_friendly_standard_error: 0.007019629050028214

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': 0.6006604295437742, 'latency_mean': 1.6647067987918853, 'latency_p50': 1.6643987894058228, 'latency_p90': 1.8414123058319092}, {'batch_size': 3, 'throughput': 1.0854893095709426, 'latency_mean': 2.7601044404506685, 'latency_p50': 2.7387136220932007, 'latency_p90': 3.05983726978302}, {'batch_size': 5, 'throughput': 1.3002859327372274, 'latency_mean': 3.824763721227646, 'latency_p50': 3.7662150859832764, 'latency_p90': 4.287122392654419}, {'batch_size': 6, 'throughput': 1.3637571971446847, 'latency_mean': 4.3886103451251985, 'latency_p50': 4.404518246650696, 'latency_p90': 4.885557174682617}, {'batch_size': 8, 'throughput': 1.4097385109307257, 'latency_mean': 5.62761394739151, 'latency_p50': 5.628679037094116, 'latency_p90': 6.3305152416229244}, {'batch_size': 10, 'throughput': 1.456721592262039, 'latency_mean': 6.819065769910813, 'latency_p50': 6.793338179588318, 'latency_p90': 7.591661667823791}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-16-full-qkv_72_v2

is_internal_developer: False

language_model: junhua024/chai_16_full_qkv100_o106_ffn106_1624

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-07-20

win_ratio: 0.4952741020793951

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-v2-mkmlizer
Waiting for job on junhua024-chai-16-full-qkv-72-v2-mkmlizer to finish
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)
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-qkv-72-v2-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v2-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)
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-v2-mkmlizer: Downloaded to shared memory in 81.315s
junhua024-chai-16-full-qkv-72-v2-mkmlizer: Checking if junhua024/chai_16_full_qkv100_o106_ffn106_1624 already exists in ChaiML
junhua024-chai-16-full-qkv-72-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo7q1nu6x, device:0
junhua024-chai-16-full-qkv-72-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-qkv-72-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-qkv-72-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-qkv-72-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v2/nvidia
junhua024-chai-16-full-qkv-72-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v2/nvidia/config.json
junhua024-chai-16-full-qkv-72-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v2/nvidia/special_tokens_map.json
junhua024-chai-16-full-qkv-72-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v2/nvidia/tokenizer_config.json
junhua024-chai-16-full-qkv-72-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v2/nvidia/tokenizer.json
junhua024-chai-16-full-qkv-72-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v2/nvidia/flywheel_model.0.safetensors
junhua024-chai-16-full-qkv-72-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:22, 15.79it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.57it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:11, 31.53it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:10, 33.18it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 28.58it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:12, 28.29it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:08, 38.69it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:10, 31.70it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 31.70it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 31.90it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:08, 38.59it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:11, 27.55it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:10, 30.12it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 33.39it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 32.81it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 33.87it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:09, 31.42it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 35.46it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.81it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 36.96it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:07, 35.50it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 32.46it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 40.96it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 29.18it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:08, 29.97it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:07, 30.38it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:07, 29.67it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 32.84it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 33.69it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:06, 31.56it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 31.27it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 42.70it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:06, 33.11it/s]
Loading 0:  46%|████▌     | 167/363 [00:05<00:05, 33.63it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 42.52it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 35.96it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 34.06it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 33.38it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 31.53it/s]
Loading 0:  55%|█████▌    | 200/363 [00:06<00:04, 34.73it/s]
Loading 0:  56%|█████▌    | 204/363 [00:06<00:04, 34.32it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:05, 29.98it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:05, 29.00it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:04, 34.11it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 31.60it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 31.45it/s]
Loading 0:  64%|██████▎   | 231/363 [00:07<00:04, 29.38it/s]
Loading 0:  65%|██████▌   | 237/363 [00:07<00:03, 36.01it/s]
Loading 0:  66%|██████▋   | 241/363 [00:07<00:03, 32.32it/s]
Loading 0:  67%|██████▋   | 245/363 [00:07<00:03, 33.48it/s]
Loading 0:  69%|██████▊   | 249/363 [00:07<00:03, 32.89it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 33.04it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 31.51it/s]
Loading 0:  72%|███████▏  | 263/363 [00:08<00:03, 28.71it/s]
Loading 0:  73%|███████▎  | 266/363 [00:08<00:03, 28.00it/s]
Loading 0:  74%|███████▍  | 269/363 [00:08<00:03, 25.97it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:03, 28.69it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 34.21it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 31.46it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 31.21it/s]
Loading 0:  81%|████████  | 294/363 [00:09<00:02, 29.29it/s]
Loading 0:  82%|████████▏ | 298/363 [00:09<00:02, 31.48it/s]
Loading 0:  83%|████████▎ | 303/363 [00:09<00:02, 29.49it/s]
Loading 0:  85%|████████▍ | 307/363 [00:09<00:01, 29.02it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 28.59it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 29.26it/s]
Loading 0:  88%|████████▊ | 320/363 [00:10<00:01, 27.07it/s]
Loading 0:  90%|█████████ | 327/363 [00:10<00:01, 31.85it/s]
Loading 0:  91%|█████████▏| 332/363 [00:10<00:00, 31.89it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 33.14it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 38.18it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 26.33it/s]
Loading 0:  97%|█████████▋| 353/363 [00:11<00:00, 24.16it/s]
Loading 0:  98%|█████████▊| 357/363 [00:11<00:00, 25.18it/s]
                                                            
Job junhua024-chai-16-full-qkv-72-v2-mkmlizer completed after 147.47s with status: succeeded
Stopping job with name junhua024-chai-16-full-qkv-72-v2-mkmlizer
Pipeline stage MKMLizer completed in 147.96s
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 junhua024-chai-16-full-qkv-72-v2
Waiting for inference service junhua024-chai-16-full-qkv-72-v2 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)
Failed to get response for submission junhua024-chai-16-full-_94000_v8: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v8-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_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 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_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_v9: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
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)
Inference service junhua024-chai-16-full-qkv-72-v2 ready after 332.3336901664734s
Pipeline stage MKMLDeployer completed in 333.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5035831928253174s
Received healthy response to inference request in 1.704286813735962s
Received healthy response to inference request in 1.6339428424835205s
Received healthy response to inference request in 1.777425765991211s
Received healthy response to inference request in 2.425745964050293s
5 requests
0 failed requests
5th percentile: 1.6480116367340087
10th percentile: 1.662080430984497
20th percentile: 1.6902180194854737
30th percentile: 1.7189146041870118
40th percentile: 1.7481701850891114
50th percentile: 1.777425765991211
60th percentile: 2.036753845214844
70th percentile: 2.2960819244384765
80th percentile: 2.4413134098052978
90th percentile: 2.472448301315308
95th percentile: 2.4880157470703126
99th percentile: 2.5004697036743164
mean time: 2.008996915817261
Pipeline stage StressChecker completed in 11.29s
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 0.66s
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 0.73s
Shutdown handler de-registered
junhua024-chai-16-full-qkv_72_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-16-full-qkv-72-v2-profiler
Waiting for inference service junhua024-chai-16-full-qkv-72-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 4697.41s
Shutdown handler de-registered
junhua024-chai-16-full-qkv_72_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-qkv_72_v2 status is now torndown due to DeploymentManager action