chaiml-opusd-v2b-opusd_33883

developer_uid: richhx

submission_id: chaiml-opusd-v2b-opusd_33883_v15

model_name: chaiml-opusd-v2b-opusd_33883_v15

model_group: ChaiML/opusd-v2b-opusdv1

status: torndown

timestamp: 2026-01-14T16:56:02+00:00

num_battles: 11578

num_wins: 6364

celo_rating: 9999.0

family_friendly_score: 0.5558000000000001

family_friendly_standard_error: 0.0070268963276826565

submission_type: basic

model_repo: ChaiML/opusd-v2b-opusdv1b-lr5e6ep2r64g8b01-int4-mixed

model_architecture: Qwen3MoeForCausalLM

model_num_parameters: 18790207488.0

best_of: 4

max_input_tokens: 2048

max_output_tokens: 80

reward_model: default

display_name: chaiml-opusd-v2b-opusd_33883_v15

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/opusd-v2b-opusdv1b-lr5e6ep2r64g8b01-int4-mixed

model_size: 19B

ranking_group: single

us_pacific_date: 2026-01-09

win_ratio: 0.5496631542580757

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': ['<|user|>', '</s>', '<|im_end|>', '</think>', '<|assistant|>', '####'], 'max_input_tokens': 2048, 'best_of': 4, 'max_output_tokens': 80}

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 0.15s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-opusd-v2b-opusd-33883-v15
Waiting for inference service chaiml-opusd-v2b-opusd-33883-v15 to be ready
Inference service chaiml-opusd-v2b-opusd-33883-v15 ready after 490.81060004234314s
Pipeline stage VLLMDeployer completed in 491.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.238325595855713s
Received healthy response to inference request in 1.828446865081787s
Received healthy response to inference request in 1.9029698371887207s
Received healthy response to inference request in 1.975337266921997s
Received healthy response to inference request in 2.2734146118164062s
Received healthy response to inference request in 1.6750938892364502s
Received healthy response to inference request in 1.8486404418945312s
Received healthy response to inference request in 2.046614408493042s
Received healthy response to inference request in 1.7298285961151123s
Received healthy response to inference request in 1.7722797393798828s
Received healthy response to inference request in 1.8627548217773438s
Received healthy response to inference request in 1.7575409412384033s
Received healthy response to inference request in 1.7012779712677002s
Received healthy response to inference request in 2.132601022720337s
Received healthy response to inference request in 1.9625170230865479s
Received healthy response to inference request in 1.7037110328674316s
Received healthy response to inference request in 1.7262518405914307s
Received healthy response to inference request in 1.9118378162384033s
Received healthy response to inference request in 1.7257308959960938s
Received healthy response to inference request in 1.9547336101531982s
Received healthy response to inference request in 1.8685061931610107s
Received healthy response to inference request in 1.8312163352966309s
Received healthy response to inference request in 1.8569824695587158s
Received healthy response to inference request in 2.36228609085083s
Received healthy response to inference request in 1.7137088775634766s
Received healthy response to inference request in 2.0854506492614746s
Received healthy response to inference request in 1.747814655303955s
Received healthy response to inference request in 2.6429312229156494s
Received healthy response to inference request in 2.024329900741577s
Received healthy response to inference request in 1.9382271766662598s
30 requests
0 failed requests
5th percentile: 1.7023728489875793
10th percentile: 1.712709093093872
20th percentile: 1.7291132450103759
30th percentile: 1.767858099937439
40th percentile: 1.8416707992553711
50th percentile: 1.8656305074691772
60th percentile: 1.922393560409546
70th percentile: 1.9663630962371825
80th percentile: 2.054381656646729
90th percentile: 2.2418344974517823
95th percentile: 2.322293925285339
99th percentile: 2.561544134616852
mean time: 1.9267120599746703
Pipeline stage StressChecker completed in 60.93s
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 0.49s
Shutdown handler de-registered
chaiml-opusd-v2b-opusd_33883_v15 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 2906.43s
Shutdown handler de-registered
chaiml-opusd-v2b-opusd_33883_v15 status is now inactive due to auto deactivation removed underperforming models
chaiml-opusd-v2b-opusd_33883_v15 status is now torndown due to DeploymentManager action