chaiml-qwen2p5-14b-hybr_69970

developer_uid: NischayDnk

submission_id: chaiml-qwen2p5-14b-hybr_69970_v1

model_name: chaiml-qwen2p5-14b-hybr_69970_v1

model_group: ChaiML/qwen2p5-14B-hybri

status: torndown

timestamp: 2025-05-13T08:22:18+00:00

num_battles: 9683

num_wins: 361

celo_rating: 720.06

family_friendly_score: 0.8692

family_friendly_standard_error: 0.004768466420139708

submission_type: basic

model_repo: ChaiML/qwen2p5-14B-hybrid-from-qwen3

model_architecture: Qwen2ForCausalLM

model_num_parameters: 14769689600.0

best_of: 5

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5191428668698476, 'latency_mean': 1.926160786151886, 'latency_p50': 1.9286088943481445, 'latency_p90': 2.1328824758529663}, {'batch_size': 3, 'throughput': 1.058867751140212, 'latency_mean': 2.8277719402313233, 'latency_p50': 2.8222869634628296, 'latency_p90': 3.1335071563720702}, {'batch_size': 5, 'throughput': 1.3639057786183795, 'latency_mean': 3.6498146831989287, 'latency_p50': 3.6116034984588623, 'latency_p90': 4.072891354560852}, {'batch_size': 6, 'throughput': 1.4652769297567494, 'latency_mean': 4.0706606090068815, 'latency_p50': 4.0914987325668335, 'latency_p90': 4.530745625495911}, {'batch_size': 8, 'throughput': 1.5886367150873786, 'latency_mean': 5.0008390009403225, 'latency_p50': 5.021925449371338, 'latency_p90': 5.569890356063842}, {'batch_size': 10, 'throughput': 1.6696713530368723, 'latency_mean': 5.94224924325943, 'latency_p50': 5.9053356647491455, 'latency_p90': 6.868926978111267}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-qwen2p5-14b-hybr_69970_v1

is_internal_developer: False

language_model: ChaiML/qwen2p5-14B-hybrid-from-qwen3

model_size: 15B

ranking_group: single

throughput_3p7s: 1.38

us_pacific_date: 2025-05-13

win_ratio: 0.03728183414231127

generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], '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 chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer
Waiting for job on chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer to finish
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║       /___/                                                         ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║                                                                     ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║                                                                     ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║                                                                     ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ║                                                                     ║
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: Downloaded to shared memory in 45.356s
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9iuk9n8d, device:0
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: quantized model in 36.466s
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: Processed model ChaiML/qwen2p5-14B-hybrid-from-qwen3 in 81.823s
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen2p5-14b-hybr-69970-v1
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen2p5-14b-hybr-69970-v1/added_tokens.json
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen2p5-14b-hybr-69970-v1/config.json
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen2p5-14b-hybr-69970-v1/special_tokens_map.json
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen2p5-14b-hybr-69970-v1/tokenizer_config.json
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen2p5-14b-hybr-69970-v1/merges.txt
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen2p5-14b-hybr-69970-v1/vocab.json
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen2p5-14b-hybr-69970-v1/tokenizer.json
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen2p5-14b-hybr-69970-v1/flywheel_model.0.safetensors
chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   3%|▎         | 15/579 [00:00<00:04, 139.52it/s]
Loading 0:   5%|▌         | 29/579 [00:00<00:04, 125.27it/s]
Loading 0:   8%|▊         | 48/579 [00:00<00:03, 152.58it/s]
Loading 0:  11%|█         | 64/579 [00:00<00:03, 142.83it/s]
Loading 0:  14%|█▍        | 81/579 [00:00<00:05, 95.07it/s] 
Loading 0:  16%|█▌        | 94/579 [00:00<00:04, 103.03it/s]
Loading 0:  18%|█▊        | 107/579 [00:00<00:04, 109.50it/s]
Loading 0:  21%|██        | 123/579 [00:01<00:03, 122.09it/s]
Loading 0:  25%|██▍       | 142/579 [00:01<00:03, 140.24it/s]
Loading 0:  27%|██▋       | 158/579 [00:01<00:03, 130.78it/s]
Loading 0:  30%|███       | 176/579 [00:01<00:02, 143.46it/s]
Loading 0:  33%|███▎      | 192/579 [00:01<00:04, 90.61it/s] 
Loading 0:  36%|███▌      | 207/579 [00:01<00:03, 101.67it/s]
Loading 0:  38%|███▊      | 221/579 [00:01<00:03, 105.55it/s]
Loading 0:  42%|████▏     | 243/579 [00:02<00:02, 121.90it/s]
Loading 0:  44%|████▍     | 257/579 [00:02<00:02, 120.30it/s]
Loading 0:  48%|████▊     | 279/579 [00:02<00:02, 137.87it/s]
Loading 0:  51%|█████▏    | 297/579 [00:02<00:02, 103.27it/s]
Loading 0:  54%|█████▎    | 310/579 [00:02<00:02, 100.92it/s]
Loading 0:  56%|█████▋    | 327/579 [00:02<00:02, 113.73it/s]
Loading 0:  59%|█████▉    | 341/579 [00:02<00:02, 114.99it/s]
Loading 0:  63%|██████▎   | 363/579 [00:03<00:01, 133.82it/s]
Loading 0:  65%|██████▌   | 378/579 [00:03<00:01, 131.23it/s]
Loading 0:  69%|██████▉   | 400/579 [00:03<00:01, 150.79it/s]
Loading 0:  72%|███████▏  | 416/579 [00:03<00:01, 96.91it/s] 
Loading 0:  75%|███████▌  | 435/579 [00:03<00:01, 111.48it/s]
Loading 0:  78%|███████▊  | 449/579 [00:03<00:01, 113.52it/s]
Loading 0:  81%|████████  | 469/579 [00:03<00:00, 132.82it/s]
Loading 0:  84%|████████▍ | 485/579 [00:04<00:00, 127.55it/s]
Loading 0:  88%|████████▊ | 507/579 [00:04<00:00, 149.41it/s]
Loading 0:  88%|████████▊ | 512/579 [00:21<00:00, 149.41it/s]
Loading 0:  89%|████████▊ | 513/579 [00:25<00:29,  2.26it/s] 
Loading 0:  90%|█████████ | 522/579 [00:25<00:20,  2.82it/s]
Loading 0:  94%|█████████▍| 544/579 [00:26<00:07,  4.80it/s]
Loading 0:  97%|█████████▋| 560/579 [00:26<00:02,  6.78it/s]
Loading 0: 100%|█████████▉| 577/579 [00:26<00:00,  9.72it/s]
                                                            
Job chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer completed after 115.42s with status: succeeded
Stopping job with name chaiml-qwen2p5-14b-hybr-69970-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.93s
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 chaiml-qwen2p5-14b-hybr-69970-v1
Waiting for inference service chaiml-qwen2p5-14b-hybr-69970-v1 to be ready
Inference service chaiml-qwen2p5-14b-hybr-69970-v1 ready after 120.45080804824829s
Pipeline stage MKMLDeployer completed in 121.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3742716312408447s
Received healthy response to inference request in 1.8298304080963135s
Received healthy response to inference request in 1.7978057861328125s
Received healthy response to inference request in 2.127610445022583s
Received healthy response to inference request in 1.9961836338043213s
5 requests
0 failed requests
5th percentile: 1.8042107105255127
10th percentile: 1.810615634918213
20th percentile: 1.8234254837036132
30th percentile: 1.863101053237915
40th percentile: 1.929642343521118
50th percentile: 1.9961836338043213
60th percentile: 2.048754358291626
70th percentile: 2.1013250827789305
80th percentile: 2.1769426822662354
90th percentile: 2.27560715675354
95th percentile: 2.3249393939971923
99th percentile: 2.364405183792114
mean time: 2.025140380859375
Pipeline stage StressChecker completed in 11.46s
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 0.93s
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 0.68s
Shutdown handler de-registered
chaiml-qwen2p5-14b-hybr_69970_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 0.09s
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 chaiml-qwen2p5-14b-hybr-69970-v1-profiler
Waiting for inference service chaiml-qwen2p5-14b-hybr-69970-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4285.49s
Shutdown handler de-registered
chaiml-qwen2p5-14b-hybr_69970_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen2p5-14b-hybr_69970_v1 status is now torndown due to DeploymentManager action