chaiml-kimid-v8a-kimidv_94399

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v8a-kimidv_94399_v2

model_name: chaiml-kimid-v8a-kimidv_94399_v2

model_group: ChaiML/kimid-v8a-kimidv6

status: torndown

timestamp: 2025-12-23T22:30:52+00:00

num_battles: 6243

num_wins: 3366

celo_rating: 1320.76

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/kimid-v8a-kimidv6-lr5e6ep2r64g2b01-int4-mixed

model_architecture: Qwen3MoeForCausalLM

model_num_parameters: 18790207488.0

best_of: 4

max_input_tokens: 2048

max_output_tokens: 72

reward_model: default

display_name: chaiml-kimid-v8a-kimidv_94399_v2

ineligible_reason: model is not deployable

is_internal_developer: True

language_model: ChaiML/kimid-v8a-kimidv6-lr5e6ep2r64g2b01-int4-mixed

model_size: 19B

ranking_group: single

us_pacific_date: 2025-12-23

win_ratio: 0.5391638635271504

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|>', '####', '<|user|>', '</s>', '<|assistant|>', '</think>'], 'max_input_tokens': 2048, 'best_of': 4, '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 0.14s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-kimid-v8a-kimidv-94399-v2
Waiting for inference service chaiml-kimid-v8a-kimidv-94399-v2 to be ready
Failed to get response for submission chaiml-kimid-v9-opusdv1_83165_v2: HTTPConnectionPool(host='chaiml-kimid-v9-opusdv1-83165-v2-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-kimid-v8a-kimidv-94399-v2 ready after 512.6479725837708s
Pipeline stage VLLMDeployer completed in 512.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7014338970184326s
Received healthy response to inference request in 1.5065548419952393s
Received healthy response to inference request in 1.6002626419067383s
Received healthy response to inference request in 1.6104295253753662s
Received healthy response to inference request in 1.7015397548675537s
Received healthy response to inference request in 1.492487907409668s
Received healthy response to inference request in 1.569284439086914s
Received healthy response to inference request in 1.5283777713775635s
Received healthy response to inference request in 1.5868346691131592s
Received healthy response to inference request in 1.7803826332092285s
Received healthy response to inference request in 2.0354912281036377s
Received healthy response to inference request in 1.8881258964538574s
Received healthy response to inference request in 1.6267468929290771s
Received healthy response to inference request in 1.5916967391967773s
Received healthy response to inference request in 1.569610595703125s
Received healthy response to inference request in 1.5854365825653076s
Received healthy response to inference request in 1.527825117111206s
Received healthy response to inference request in 1.5721466541290283s
Received healthy response to inference request in 1.8352482318878174s
Received healthy response to inference request in 1.756126880645752s
Received healthy response to inference request in 1.6081697940826416s
Received healthy response to inference request in 1.8857872486114502s
Received healthy response to inference request in 2.1022379398345947s
Received healthy response to inference request in 1.7318668365478516s
Received healthy response to inference request in 1.5607552528381348s
Received healthy response to inference request in 2.067580223083496s
Received healthy response to inference request in 1.5760912895202637s
Received healthy response to inference request in 1.6776340007781982s
Received healthy response to inference request in 1.8567194938659668s
Received healthy response to inference request in 1.5993571281433105s
30 requests
0 failed requests
5th percentile: 1.5161264657974243
10th percentile: 1.5283225059509278
20th percentile: 1.569545364379883
30th percentile: 1.5826329946517945
40th percentile: 1.5962929725646973
50th percentile: 1.609299659729004
60th percentile: 1.687153959274292
70th percentile: 1.7391448497772215
80th percentile: 1.8395424842834474
90th percentile: 1.9028624296188357
95th percentile: 2.0531401753425595
99th percentile: 2.092187201976776
mean time: 1.6910747369130452
Pipeline stage StressChecker completed in 53.31s
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 0.59s
Shutdown handler de-registered
chaiml-kimid-v8a-kimidv_94399_v2 status is now deployed due to DeploymentManager action
chaiml-kimid-v8a-kimidv_94399_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-kimid-v8a-kimidv_94399_v2 status is now protected due to ABTestQueueItem
chaiml-kimid-v8a-kimidv_94399_v2 status is now protected due to ABTestQueueItem