developer_uid: richhx
submission_id: chaiml-collin-servant-p_16591_v1
model_name: chaiml-collin-servant-p_16591_v1
model_group: ChaiML/Collin-Servant-Pr
status: torndown
timestamp: 2025-07-07T21:57:06+00:00
num_battles: 6364
num_wins: 3102
celo_rating: 1281.36
family_friendly_score: 0.5176000000000001
family_friendly_standard_error: 0.007066685786137658
submission_type: basic
model_repo: ChaiML/Collin-Servant-Prince-forbidden-love_S250330035636
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.518076388120965, 'latency_mean': 1.9301198387145997, 'latency_p50': 1.9382039308547974, 'latency_p90': 2.128168749809265}, {'batch_size': 3, 'throughput': 1.047822450625964, 'latency_mean': 2.8624339401721954, 'latency_p50': 2.8906015157699585, 'latency_p90': 3.133010411262512}, {'batch_size': 5, 'throughput': 1.3522150754008777, 'latency_mean': 3.685076142549515, 'latency_p50': 3.664133667945862, 'latency_p90': 4.140481805801391}, {'batch_size': 6, 'throughput': 1.4553122432190253, 'latency_mean': 4.100305329561234, 'latency_p50': 4.069947242736816, 'latency_p90': 4.598204779624939}, {'batch_size': 8, 'throughput': 1.5698071449616295, 'latency_mean': 5.052616648674011, 'latency_p50': 5.075363993644714, 'latency_p90': 5.657683110237121}, {'batch_size': 10, 'throughput': 1.6516905408501847, 'latency_mean': 6.008971107006073, 'latency_p50': 6.051767349243164, 'latency_p90': 6.728523874282837}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-collin-servant-p_16591_v1
ineligible_reason: num_battles<10000
is_internal_developer: True
language_model: ChaiML/Collin-Servant-Prince-forbidden-love_S250330035636
model_size: 24B
ranking_group: single
throughput_3p7s: 1.36
us_pacific_date: 2025-07-07
win_ratio: 0.48742928975487115
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': ['</s>', '####\n', '\n', '####', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{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 MKMLizer
Starting job with name chaiml-collin-servant-p-16591-v1-mkmlizer
Waiting for job on chaiml-collin-servant-p-16591-v1-mkmlizer to finish
chaiml-collin-servant-p-16591-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-collin-servant-p-16591-v1-mkmlizer: ║                                                                     ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║                                                                     ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║                                                                     ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║                                                                     ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ║                                                                     ║
chaiml-collin-servant-p-16591-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-collin-servant-p-16591-v1-mkmlizer: Downloaded to shared memory in 140.046s
chaiml-collin-servant-p-16591-v1-mkmlizer: Checking if ChaiML/Collin-Servant-Prince-forbidden-love_S250330035636 already exists in ChaiML
chaiml-collin-servant-p-16591-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4sado48i, device:0
chaiml-collin-servant-p-16591-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-collin-servant-p-16591-v1-mkmlizer: quantized model in 46.486s
chaiml-collin-servant-p-16591-v1-mkmlizer: Processed model ChaiML/Collin-Servant-Prince-forbidden-love_S250330035636 in 186.532s
chaiml-collin-servant-p-16591-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-collin-servant-p-16591-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-collin-servant-p-16591-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-collin-servant-p-16591-v1/nvidia
chaiml-collin-servant-p-16591-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-collin-servant-p-16591-v1/nvidia/config.json
chaiml-collin-servant-p-16591-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-collin-servant-p-16591-v1/nvidia/special_tokens_map.json
chaiml-collin-servant-p-16591-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-collin-servant-p-16591-v1/nvidia/tokenizer_config.json
chaiml-collin-servant-p-16591-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-collin-servant-p-16591-v1/nvidia/tokenizer.json
chaiml-collin-servant-p-16591-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-collin-servant-p-16591-v1/nvidia/flywheel_model.1.safetensors
chaiml-collin-servant-p-16591-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-collin-servant-p-16591-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-collin-servant-p-16591-v1-mkmlizer completed after 219.94s with status: succeeded
Stopping job with name chaiml-collin-servant-p-16591-v1-mkmlizer
Pipeline stage MKMLizer completed in 220.54s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-collin-servant-p-16591-v1
Waiting for inference service chaiml-collin-servant-p-16591-v1 to be ready
Inference service chaiml-collin-servant-p-16591-v1 ready after 190.93697547912598s
Pipeline stage MKMLDeployer completed in 191.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.602198362350464s
Received healthy response to inference request in 1.9872608184814453s
Received healthy response to inference request in 2.3745663166046143s
Received healthy response to inference request in 1.8109674453735352s
Received healthy response to inference request in 2.153238534927368s
5 requests
0 failed requests
5th percentile: 1.846226119995117
10th percentile: 1.8814847946166993
20th percentile: 1.9520021438598634
30th percentile: 2.0204563617706297
40th percentile: 2.086847448348999
50th percentile: 2.153238534927368
60th percentile: 2.2417696475982667
70th percentile: 2.330300760269165
80th percentile: 2.420092725753784
90th percentile: 2.511145544052124
95th percentile: 2.556671953201294
99th percentile: 2.59309308052063
mean time: 2.1856462955474854
Pipeline stage StressChecker completed in 12.51s
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 0.69s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.73s
Shutdown handler de-registered
chaiml-collin-servant-p_16591_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6971.51s
Shutdown handler de-registered
chaiml-collin-servant-p_16591_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-collin-servant-p_16591_v1 status is now protected
chaiml-collin-servant-p_16591_v1 status is now protected
chaiml-collin-servant-p_16591_v1 status is now torndown due to DeploymentManager action