developer_uid: chai_backend_admin
submission_id: chaiml-will-qwen3-235b-_55761_v1
model_name: chaiml-will-qwen3-235b-_55761_v1
model_group: ChaiML/will-qwen3-235b-a
status: torndown
timestamp: 2025-12-24T19:31:48+00:00
num_battles: 5890
num_wins: 3326
celo_rating: 1338.46
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/will-qwen3-235b-a22b-instruct-2507-opus-distil-500k-qwen235b-dpo-8k-r1-13dd8f6f-int4-mixed
model_architecture: Qwen3MoeForCausalLM
model_num_parameters: 18790207488.0
best_of: 8
max_input_tokens: 1992
max_output_tokens: 80
reward_model: default
display_name: chaiml-will-qwen3-235b-_55761_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/will-qwen3-235b-a22b-instruct-2507-opus-distil-500k-qwen235b-dpo-8k-r1-13dd8f6f-int4-mixed
model_size: 19B
ranking_group: single
us_pacific_date: 2025-12-24
win_ratio: 0.5646859083191851
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|>', '<|im_end|>', '####', '</s>', '</think>', '<|assistant|>'], 'max_input_tokens': 1992, 'best_of': 8, 'max_output_tokens': 80}
formatter: {'memory_template': '<|im_start|>system\nYou are {bot_name} engaged in a roleplay with user.<|im_end|>\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 0.25s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-will-qwen3-235b-55761-v1
Waiting for inference service chaiml-will-qwen3-235b-55761-v1 to be ready
Inference service chaiml-will-qwen3-235b-55761-v1 ready after 486.94402742385864s
Pipeline stage VLLMDeployer completed in 488.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1622889041900635s
Received healthy response to inference request in 2.3227016925811768s
Received healthy response to inference request in 2.238787889480591s
Received healthy response to inference request in 2.297252893447876s
Received healthy response to inference request in 2.126826047897339s
Received healthy response to inference request in 2.0271546840667725s
Received healthy response to inference request in 2.0065414905548096s
Received healthy response to inference request in 2.240539789199829s
Received healthy response to inference request in 1.9964418411254883s
Received healthy response to inference request in 2.0013341903686523s
Received healthy response to inference request in 2.065453290939331s
Received healthy response to inference request in 2.1526806354522705s
Received healthy response to inference request in 2.1089067459106445s
Received healthy response to inference request in 2.348438024520874s
Received healthy response to inference request in 2.391899347305298s
Received healthy response to inference request in 1.964172124862671s
Received healthy response to inference request in 2.527724027633667s
Received healthy response to inference request in 2.033250093460083s
Received healthy response to inference request in 2.1887447834014893s
Received healthy response to inference request in 2.225851058959961s
Received healthy response to inference request in 2.0765175819396973s
Received healthy response to inference request in 2.5869216918945312s
Received healthy response to inference request in 2.232330322265625s
Received healthy response to inference request in 1.9798283576965332s
Received healthy response to inference request in 2.0203096866607666s
Received healthy response to inference request in 2.0163564682006836s
Received healthy response to inference request in 2.045318603515625s
Received healthy response to inference request in 2.066938638687134s
Received healthy response to inference request in 2.6631743907928467s
Received healthy response to inference request in 2.0598788261413574s
30 requests
0 failed requests
5th percentile: 1.987304425239563
10th percentile: 2.000844955444336
20th percentile: 2.01951904296875
30th percentile: 2.0416980504989626
40th percentile: 2.0663444995880127
50th percentile: 2.1178663969039917
60th percentile: 2.1728712558746337
70th percentile: 2.2342675924301147
80th percentile: 2.302342653274536
90th percentile: 2.4054818153381348
95th percentile: 2.560282742977142
99th percentile: 2.641061108112335
mean time: 2.1724854707717896
Pipeline stage StressChecker completed in 68.62s
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 1.85s
Shutdown handler de-registered
chaiml-will-qwen3-235b-_55761_v1 status is now deployed due to DeploymentManager action
chaiml-will-qwen3-235b-_55761_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-will-qwen3-235b-_55761_v1 status is now torndown due to DeploymentManager action