developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwi_77425_v4
model_name: chaiml-mn24b-v2preferwi_77425_v4
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-24T18:36:49+00:00
num_battles: 5439
num_wins: 2765
celo_rating: 1271.97
family_friendly_score: 0.5516
family_friendly_standard_error: 0.007033312732987209
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_nonl_bo4_tune5
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': 0.5493156843164366, 'latency_mean': 1.820342618227005, 'latency_p50': 1.8021959066390991, 'latency_p90': 2.0379770040512084}, {'batch_size': 3, 'throughput': 1.114563974674148, 'latency_mean': 2.6782993388175966, 'latency_p50': 2.65302050113678, 'latency_p90': 3.0080819129943848}, {'batch_size': 5, 'throughput': 1.4392701026054344, 'latency_mean': 3.4547923684120176, 'latency_p50': 3.438078761100769, 'latency_p90': 3.9807004690170285}, {'batch_size': 6, 'throughput': 1.5462500133844708, 'latency_mean': 3.846237899065018, 'latency_p50': 3.839945673942566, 'latency_p90': 4.353636932373047}, {'batch_size': 8, 'throughput': 1.6810785625924265, 'latency_mean': 4.722701007127762, 'latency_p50': 4.726656556129456, 'latency_p90': 5.3613602876663204}, {'batch_size': 10, 'throughput': 1.7836408009321598, 'latency_mean': 5.559740147590637, 'latency_p50': 5.554667949676514, 'latency_p90': 6.318049812316895}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwi_77425_v4
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_nonl_bo4_tune5
model_size: 24B
ranking_group: single
throughput_3p7s: 1.52
us_pacific_date: 2025-09-24
win_ratio: 0.5083655083655083
generation_params: {'temperature': 0.75, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {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-mn24b-v2preferwi-77425-v4-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwi-77425-v4-mkmlizer to finish
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: Downloaded to shared memory in 147.475s
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_nonl_bo4_tune5 already exists in ChaiML
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpf5svy1ys, device:0
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: quantized model in 284.529s
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_nonl_bo4_tune5 in 432.004s
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-77425-v4/nvidia
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-77425-v4/nvidia/config.json
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-77425-v4/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-77425-v4/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-77425-v4/nvidia/tokenizer.json
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-77425-v4/nvidia/flywheel_model.1.safetensors
chaiml-mn24b-v2preferwi-77425-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-77425-v4/nvidia/flywheel_model.0.safetensors
Job chaiml-mn24b-v2preferwi-77425-v4-mkmlizer completed after 522.52s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwi-77425-v4-mkmlizer
Pipeline stage MKMLizer completed in 522.98s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mn24b-v2preferwi-77425-v4
Waiting for inference service chaiml-mn24b-v2preferwi-77425-v4 to be ready
Inference service chaiml-mn24b-v2preferwi-77425-v4 ready after 50.56000542640686s
Pipeline stage MKMLDeployer completed in 51.17s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.0563101768493652s
Received healthy response to inference request in 1.7452504634857178s
Received healthy response to inference request in 1.6476738452911377s
Received healthy response to inference request in 2.076951026916504s
5 requests
1 failed requests
5th percentile: 1.6671891689300538
10th percentile: 1.6867044925689698
20th percentile: 1.7257351398468017
30th percentile: 1.8074624061584472
40th percentile: 1.9318862915039063
50th percentile: 2.0563101768493652
60th percentile: 2.0645665168762206
70th percentile: 2.072822856903076
80th percentile: 5.685056591033939
90th percentile: 12.901267719268802
95th percentile: 16.50937328338623
99th percentile: 19.395857734680174
mean time: 5.528732872009277
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6866865158081055s
Received healthy response to inference request in 2.1355302333831787s
Received healthy response to inference request in 2.8062517642974854s
Received healthy response to inference request in 1.7528817653656006s
Received healthy response to inference request in 1.6708486080169678s
5 requests
0 failed requests
5th percentile: 1.6740161895751953
10th percentile: 1.6771837711334228
20th percentile: 1.683518934249878
30th percentile: 1.6999255657196044
40th percentile: 1.7264036655426025
50th percentile: 1.7528817653656006
60th percentile: 1.9059411525726317
70th percentile: 2.059000539779663
80th percentile: 2.26967453956604
90th percentile: 2.5379631519317627
95th percentile: 2.672107458114624
99th percentile: 2.779422903060913
mean time: 2.0104397773742675
Pipeline stage StressChecker completed in 40.34s
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 0.65s
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 0.61s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_77425_v4 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2861.58s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_77425_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwi_77425_v4 status is now torndown due to DeploymentManager action