chaiml-opusd-v2b-opusd_33883

developer_uid: richhx

submission_id: chaiml-opusd-v2b-opusd_33883_v18

model_name: chaiml-opusd-v2b-opusd_33883_v18

model_group: ChaiML/opusd-v2b-opusdv1

status: torndown

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

num_battles: 12064

num_wins: 6488

celo_rating: 1323.9

family_friendly_score: 0.548

family_friendly_standard_error: 0.0070384089111105224

submission_type: basic

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

model_architecture: Qwen3MoeForCausalLM

model_num_parameters: 18790207488.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 80

reward_model: default

display_name: chaiml-opusd-v2b-opusd_33883_v18

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: 0.5377984084880637

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': ['<|im_end|>', '</think>', '####', '</s>', '<|user|>', '<|assistant|>'], 'max_input_tokens': 1024, 'best_of': 8, '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-v18
Waiting for inference service chaiml-opusd-v2b-opusd-33883-v18 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission chaiml-kimid-v10-nonam_50547_v11: HTTPConnectionPool(host='chaiml-kimid-v10-nonam-50547-v11-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-opusd-v2b-opusd-33883-v18 ready after 490.87755370140076s
Pipeline stage VLLMDeployer completed in 491.69s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.040060043334961s
Received healthy response to inference request in 2.656668186187744s
Received healthy response to inference request in 2.0917153358459473s
Received healthy response to inference request in 2.1020102500915527s
Received healthy response to inference request in 2.1523823738098145s
Received healthy response to inference request in 1.8911452293395996s
Received healthy response to inference request in 1.9881079196929932s
Received healthy response to inference request in 2.198733329772949s
Received healthy response to inference request in 1.991776466369629s
Received healthy response to inference request in 2.0237932205200195s
Failed to get response for submission chaiml-kimid-v10-nonam_50547_v12: HTTPConnectionPool(host='chaiml-kimid-v10-nonam-50547-v12-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 1.984055995941162s
Received healthy response to inference request in 2.0317089557647705s
Received healthy response to inference request in 1.9239318370819092s
Received healthy response to inference request in 2.2839012145996094s
Received healthy response to inference request in 1.9853363037109375s
Received healthy response to inference request in 2.196361541748047s
Received healthy response to inference request in 2.2943263053894043s
Received healthy response to inference request in 1.9884302616119385s
Received healthy response to inference request in 2.0409727096557617s
Received healthy response to inference request in 2.365297555923462s
Received healthy response to inference request in 2.136436700820923s
Received healthy response to inference request in 1.9585278034210205s
Received healthy response to inference request in 2.862919569015503s
Received healthy response to inference request in 2.179334878921509s
Received healthy response to inference request in 2.1377313137054443s
Received healthy response to inference request in 1.9611923694610596s
Received healthy response to inference request in 2.3767921924591064s
Received healthy response to inference request in 2.489955186843872s
Received healthy response to inference request in 1.9537599086761475s
Received healthy response to inference request in 1.915912389755249s
30 requests
0 failed requests
5th percentile: 1.9195211410522461
10th percentile: 1.9507771015167237
20th percentile: 1.9794832706451415
30th percentile: 1.988333559036255
40th percentile: 2.02854266166687
50th percentile: 2.0663440227508545
60th percentile: 2.1369545459747314
70th percentile: 2.18444287776947
80th percentile: 2.285986232757568
90th percentile: 2.388108491897583
95th percentile: 2.5816473364830013
99th percentile: 2.8031066679954533
mean time: 2.1401092449824017
Pipeline stage StressChecker completed in 67.07s
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 0.63s
Shutdown handler de-registered
chaiml-opusd-v2b-opusd_33883_v18 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 5453.19s
Shutdown handler de-registered
chaiml-opusd-v2b-opusd_33883_v18 status is now torndown due to DeploymentManager action