chaiml-kimid-v8b-kimidv_63800

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v8b-kimidv_63800_v2

model_name: chaiml-kimid-v8b-kimidv_63800_v2

model_group: ChaiML/kimid-v8b-kimidv5

status: torndown

timestamp: 2026-01-16T17:07:03+00:00

num_battles: 7136

num_wins: 3983

celo_rating: 1333.98

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/kimid-v8b-kimidv5a-lr5e6ep2r64g4b01-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-kimid-v8b-kimidv_63800_v2

ineligible_reason: model is not deployable

is_internal_developer: True

language_model: ChaiML/kimid-v8b-kimidv5a-lr5e6ep2r64g4b01-int4-mixed

model_size: 19B

ranking_group: single

us_pacific_date: 2025-12-23

win_ratio: 0.5581558295964125

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|>', '<|assistant|>', '<|im_end|>', '</s>', '####', '</think>'], '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 0.13s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-kimid-v8b-kimidv-63800-v2
Waiting for inference service chaiml-kimid-v8b-kimidv-63800-v2 to be ready
Failed to get response for submission chaiml-ssnew-v5-dpo-lr_24415_v17: ('http://chaiml-ssnew-v5-dpo-lr-24415-v17-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:44704->127.0.0.1:8080: read: connection reset by peer\n')
Inference service chaiml-kimid-v8b-kimidv-63800-v2 ready after 461.31595730781555s
Pipeline stage VLLMDeployer completed in 461.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.931419849395752s
Received healthy response to inference request in 1.7368764877319336s
Received healthy response to inference request in 1.791104793548584s
Received healthy response to inference request in 1.7062993049621582s
Received healthy response to inference request in 2.248469829559326s
Received healthy response to inference request in 1.7454895973205566s
Received healthy response to inference request in 1.6805806159973145s
Received healthy response to inference request in 2.287097692489624s
Received healthy response to inference request in 1.7590782642364502s
Received healthy response to inference request in 1.7499940395355225s
Received healthy response to inference request in 1.6938502788543701s
Received healthy response to inference request in 1.6724238395690918s
Received healthy response to inference request in 1.6545062065124512s
Received healthy response to inference request in 1.6916837692260742s
Received healthy response to inference request in 1.814697504043579s
Received healthy response to inference request in 1.8678946495056152s
Received healthy response to inference request in 2.0136075019836426s
Received healthy response to inference request in 1.8576269149780273s
Received healthy response to inference request in 1.9831452369689941s
Received healthy response to inference request in 1.8271360397338867s
Received healthy response to inference request in 1.7606091499328613s
Received healthy response to inference request in 1.7080740928649902s
Received healthy response to inference request in 1.6838645935058594s
Received healthy response to inference request in 1.767627239227295s
Received healthy response to inference request in 1.6840808391571045s
Received healthy response to inference request in 1.6897468566894531s
Received healthy response to inference request in 1.7419583797454834s
Received healthy response to inference request in 2.089294910430908s
Received healthy response to inference request in 1.7001991271972656s
Received healthy response to inference request in 1.8828039169311523s
30 requests
0 failed requests
5th percentile: 1.676094388961792
10th percentile: 1.6835361957550048
20th percentile: 1.69129638671875
30th percentile: 1.7044692516326905
40th percentile: 1.7399256229400635
50th percentile: 1.7545361518859863
60th percentile: 1.7770182609558105
70th percentile: 1.8362833023071288
80th percentile: 1.8925271034240725
90th percentile: 2.021176242828369
95th percentile: 2.1768411159515377
99th percentile: 2.2758956122398377
mean time: 1.8140413840611775
Pipeline stage StressChecker completed in 56.77s
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 0.71s
Shutdown handler de-registered
chaiml-kimid-v8b-kimidv_63800_v2 status is now deployed due to DeploymentManager action
chaiml-kimid-v8b-kimidv_63800_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-kimid-v8b-kimidv_63800_v2 status is now protected due to ABTestQueueItem
chaiml-kimid-v8b-kimidv_63800_v2 status is now torndown due to DeploymentManager action