chaiml-kimid-v4a-q235-2k

developer_uid: chai_backend_admin
submission_id: chaiml-kimid-v4a-q235-2k_v1
model_name: chaiml-kimid-v4a-q235-2k_v1
model_group: ChaiML/kimid-v4a-q235-2k
status: inactive
timestamp: 2025-12-09T18:37:05+00:00
num_battles: 6501
num_wins: 3295
celo_rating: 1302.69
family_friendly_score: 0.5218
family_friendly_standard_error: 0.007064343706247595
submission_type: basic
model_repo: ChaiML/kimid-v4a-q235-2k
model_architecture: Qwen3MoeForCausalLM
model_num_parameters: 18790207488.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 72
reward_model: default
display_name: chaiml-kimid-v4a-q235-2k_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/kimid-v4a-q235-2k
model_size: 19B
ranking_group: single
us_pacific_date: 2025-12-09
win_ratio: 0.5068451007537302
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': ['</s>', '####', '<|im_end|>', '<|user|>', '</think>', '<|assistant|>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 72}
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s persona: {memory}<|im_end|>\n", 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
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 VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.51s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-kimid-v4a-q235-2k-v1
Waiting for inference service chaiml-kimid-v4a-q235-2k-v1 to be ready
Inference service chaiml-qwen3-235b-a22b-13233-v1 ready after 486.43226957321167s
Pipeline stage VLLMDeployer completed in 487.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6321561336517334s
Received healthy response to inference request in 1.993988275527954s
Received healthy response to inference request in 2.3837087154388428s
Received healthy response to inference request in 1.4881682395935059s
Received healthy response to inference request in 1.890869140625s
Received healthy response to inference request in 1.8058178424835205s
Received healthy response to inference request in 1.8059470653533936s
Received healthy response to inference request in 2.932853937149048s
Received healthy response to inference request in 1.8793082237243652s
Received healthy response to inference request in 2.4703493118286133s
Received healthy response to inference request in 1.8774974346160889s
Received healthy response to inference request in 1.6038942337036133s
Received healthy response to inference request in 1.6912939548492432s
Received healthy response to inference request in 2.3012397289276123s
Received healthy response to inference request in 1.936863899230957s
Received healthy response to inference request in 1.524482250213623s
Received healthy response to inference request in 1.759728193283081s
Received healthy response to inference request in 1.8096106052398682s
Received healthy response to inference request in 2.377040386199951s
Received healthy response to inference request in 1.4458727836608887s
Received healthy response to inference request in 1.7264354228973389s
Received healthy response to inference request in 1.6110868453979492s
Received healthy response to inference request in 2.449134349822998s
Received healthy response to inference request in 2.212009906768799s
Received healthy response to inference request in 1.6271474361419678s
Received healthy response to inference request in 1.8121490478515625s
Received healthy response to inference request in 1.8937151432037354s
Received healthy response to inference request in 1.8491930961608887s
Received healthy response to inference request in 1.6193532943725586s
Received healthy response to inference request in 1.6004054546356201s
30 requests
0 failed requests
5th percentile: 1.5045095443725587
10th percentile: 1.5928131341934204
20th percentile: 1.6177000045776366
30th percentile: 1.7158929824829101
40th percentile: 1.8058953762054444
50th percentile: 1.8306710720062256
60th percentile: 1.8839325904846191
70th percentile: 1.954001212120056
80th percentile: 2.3163998603820803
90th percentile: 2.4512558460235594
95th percentile: 2.559343063831329
99th percentile: 2.845651574134827
mean time: 1.9337106784184774
Pipeline stage StressChecker completed in 77.38s
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 3.35s
Shutdown handler de-registered
chaiml-qwen3-235b-a22b-_13233_v1 status is now deployed due to DeploymentManager action
Inference service chaiml-wb-cai-hq-ep2-rh-79474-v1 ready after 506.4368827342987s
Pipeline stage VLLMDeployer completed in 508.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.514648914337158s
Received healthy response to inference request in 2.0821170806884766s
Received healthy response to inference request in 1.7333531379699707s
Received healthy response to inference request in 1.7409148216247559s
Received healthy response to inference request in 1.7834579944610596s
Received healthy response to inference request in 1.6179649829864502s
Received healthy response to inference request in 1.6199674606323242s
Received healthy response to inference request in 2.4458470344543457s
Received healthy response to inference request in 1.9272096157073975s
Received healthy response to inference request in 2.4170942306518555s
Received healthy response to inference request in 1.8914735317230225s
Received healthy response to inference request in 2.0802342891693115s
Received healthy response to inference request in 1.6009385585784912s
Received healthy response to inference request in 2.276395082473755s
Received healthy response to inference request in 1.9702963829040527s
Received healthy response to inference request in 1.6909735202789307s
Received healthy response to inference request in 1.6640613079071045s
Received healthy response to inference request in 1.8561911582946777s
Received healthy response to inference request in 1.759638786315918s
Received healthy response to inference request in 2.074885845184326s
Received healthy response to inference request in 1.7964279651641846s
Received healthy response to inference request in 1.9069781303405762s
Received healthy response to inference request in 1.7689859867095947s
Received healthy response to inference request in 2.0704188346862793s
Received healthy response to inference request in 1.8551867008209229s
Received healthy response to inference request in 1.9331834316253662s
Received healthy response to inference request in 2.679055690765381s
Received healthy response to inference request in 3.1600522994995117s
Received healthy response to inference request in 1.6583235263824463s
Received healthy response to inference request in 2.310734272003174s
30 requests
0 failed requests
5th percentile: 1.6188660979270935
10th percentile: 1.654487919807434
20th percentile: 1.7248772144317628
30th percentile: 1.7661818265914917
40th percentile: 1.8316832065582276
50th percentile: 1.8992258310317993
60th percentile: 1.9480286121368409
70th percentile: 2.076490378379822
80th percentile: 2.283262920379639
90th percentile: 2.452727222442627
95th percentile: 2.60507264137268
99th percentile: 3.0205632829666142
mean time: 1.9962336858113607
Pipeline stage StressChecker completed in 75.20s
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 2.00s
Shutdown handler de-registered
chaiml-wb-cai-hq-ep2-rh_79474_v1 status is now deployed due to DeploymentManager action
Inference service chaiml-kimid-v4a-q235-n-98827-v1 ready after 506.63436007499695s
Pipeline stage VLLMDeployer completed in 509.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.437957763671875s
Received healthy response to inference request in 1.8660833835601807s
Received healthy response to inference request in 1.6557378768920898s
Received healthy response to inference request in 2.04897141456604s
Received healthy response to inference request in 2.4746713638305664s
Received healthy response to inference request in 1.7015624046325684s
Received healthy response to inference request in 1.728874921798706s
Received healthy response to inference request in 1.8407230377197266s
Received healthy response to inference request in 1.88604736328125s
Received healthy response to inference request in 1.9493658542633057s
Received healthy response to inference request in 1.7483203411102295s
Received healthy response to inference request in 1.8797354698181152s
Received healthy response to inference request in 1.9974431991577148s
Received healthy response to inference request in 1.6983764171600342s
Received healthy response to inference request in 1.728520154953003s
Received healthy response to inference request in 2.591203451156616s
Received healthy response to inference request in 2.025508165359497s
Received healthy response to inference request in 2.662153482437134s
Received healthy response to inference request in 1.679048776626587s
Received healthy response to inference request in 1.7329211235046387s
Received healthy response to inference request in 1.7749159336090088s
Received healthy response to inference request in 2.4132866859436035s
Received healthy response to inference request in 2.265421152114868s
Received healthy response to inference request in 1.7928907871246338s
Received healthy response to inference request in 1.8956217765808105s
Received healthy response to inference request in 2.130155324935913s
Received healthy response to inference request in 2.648062229156494s
Received healthy response to inference request in 2.4322335720062256s
Received healthy response to inference request in 1.8901081085205078s
Received healthy response to inference request in 1.7815823554992676s
30 requests
0 failed requests
5th percentile: 1.6877462148666382
10th percentile: 1.701243805885315
20th percentile: 1.732111883163452
30th percentile: 1.77958242893219
40th percentile: 1.8559392452239991
50th percentile: 1.888077735900879
60th percentile: 1.9685967922210692
70th percentile: 2.0733265876770015
80th percentile: 2.417076063156128
90th percentile: 2.4863245725631717
95th percentile: 2.6224757790565487
99th percentile: 2.6580670189857485
mean time: 2.0119167963663735
Pipeline stage StressChecker completed in 71.72s
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 1.84s
Shutdown handler de-registered
chaiml-kimid-v4a-q235-n_98827_v1 status is now deployed due to DeploymentManager action
Inference service chaiml-kimid-v4a-q235-2k-v1 ready after 506.5493803024292s
Pipeline stage VLLMDeployer completed in 508.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.365504503250122s
Received healthy response to inference request in 1.7309951782226562s
Received healthy response to inference request in 2.6362764835357666s
Received healthy response to inference request in 2.3866899013519287s
Received healthy response to inference request in 2.160038471221924s
Received healthy response to inference request in 1.6770801544189453s
Received healthy response to inference request in 1.9571325778961182s
Received healthy response to inference request in 2.31244158744812s
Received healthy response to inference request in 1.7171757221221924s
Received healthy response to inference request in 2.3580875396728516s
Received healthy response to inference request in 1.841383695602417s
Received healthy response to inference request in 2.9936394691467285s
Received healthy response to inference request in 1.670422077178955s
Received healthy response to inference request in 2.4214632511138916s
Received healthy response to inference request in 1.9800126552581787s
Received healthy response to inference request in 2.126061201095581s
Received healthy response to inference request in 1.7301971912384033s
Received healthy response to inference request in 1.9551112651824951s
Received healthy response to inference request in 2.801905870437622s
Received healthy response to inference request in 1.7548694610595703s
Received healthy response to inference request in 2.029813766479492s
Received healthy response to inference request in 1.847456455230713s
Received healthy response to inference request in 1.609503984451294s
Received healthy response to inference request in 2.405778408050537s
Received healthy response to inference request in 2.5204763412475586s
Received healthy response to inference request in 2.543592691421509s
Received healthy response to inference request in 1.9383430480957031s
Received healthy response to inference request in 1.704087495803833s
Received healthy response to inference request in 2.105729818344116s
Received healthy response to inference request in 2.634572982788086s
30 requests
0 failed requests
5th percentile: 1.6734182119369507
10th percentile: 1.7013867616653442
20th percentile: 1.7308355808258056
30th percentile: 1.8456346273422242
40th percentile: 1.956324052810669
50th percentile: 2.067771792411804
60th percentile: 2.2209997177124023
70th percentile: 2.371860122680664
80th percentile: 2.4412658691406253
90th percentile: 2.634743332862854
95th percentile: 2.7273726463317867
99th percentile: 2.938036725521088
mean time: 2.1305281082789103
Pipeline stage StressChecker completed in 70.01s
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 1.33s
Shutdown handler de-registered
chaiml-kimid-v4a-q235-2k_v1 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
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2195.80s
Shutdown handler de-registered
chaiml-kimid-v4a-q235-2k_v1 status is now inactive due to auto deactivation removed underperforming models