developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwin_4431_v2
model_name: chaiml-mn24b-v2preferwin_4431_v2
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-17T04:21:31+00:00
num_battles: 6440
num_wins: 3331
celo_rating: 1266.15
family_friendly_score: 0.5791999999999999
family_friendly_standard_error: 0.006981795757539746
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_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': 0.5508424209972137, 'latency_mean': 1.8152813136577606, 'latency_p50': 1.8257617950439453, 'latency_p90': 2.0164477109909056}, {'batch_size': 3, 'throughput': 1.1230914378817547, 'latency_mean': 2.6706304430961607, 'latency_p50': 2.664088726043701, 'latency_p90': 3.0348397970199583}, {'batch_size': 5, 'throughput': 1.424353142173334, 'latency_mean': 3.478496427536011, 'latency_p50': 3.4802392721176147, 'latency_p90': 3.9197807550430297}, {'batch_size': 6, 'throughput': 1.5405924181742783, 'latency_mean': 3.871238626241684, 'latency_p50': 3.8712064027786255, 'latency_p90': 4.36278190612793}, {'batch_size': 8, 'throughput': 1.6981188053520695, 'latency_mean': 4.6755212056636815, 'latency_p50': 4.6611487865448, 'latency_p90': 5.268703985214233}, {'batch_size': 10, 'throughput': 1.7661056806011006, 'latency_mean': 5.612313560247421, 'latency_p50': 5.642568349838257, 'latency_p90': 6.4011215448379515}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwin_4431_v2
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_bo4_tune5
model_size: 24B
ranking_group: single
throughput_3p7s: 1.5
us_pacific_date: 2025-09-16
win_ratio: 0.5172360248447205
generation_params: {'temperature': 0.65, '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-v2preferwin-4431-v2-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwin-4431-v2-mkmlizer to finish
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: Downloaded to shared memory in 55.198s
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_bo4_tune5 already exists in ChaiML
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp7vim7kea, device:0
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: quantized model in 286.719s
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_bo4_tune5 in 341.917s
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-4431-v2/nvidia
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-4431-v2/nvidia/config.json
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-4431-v2/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-4431-v2/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-4431-v2/nvidia/flywheel_model.1.safetensors
chaiml-mn24b-v2preferwin-4431-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-4431-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-mn24b-v2preferwin-4431-v2-mkmlizer completed after 469.22s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwin-4431-v2-mkmlizer
Pipeline stage MKMLizer completed in 469.71s
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-v2preferwin-4431-v2
Waiting for inference service chaiml-mn24b-v2preferwin-4431-v2 to be ready
Inference service chaiml-mn24b-v2preferwin-4431-v2 ready after 40.56382966041565s
Pipeline stage MKMLDeployer completed in 41.10s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4333865642547607s
Received healthy response to inference request in 1.714705467224121s
Received healthy response to inference request in 1.7099831104278564s
Received healthy response to inference request in 1.7152142524719238s
Received healthy response to inference request in 1.2492930889129639s
5 requests
0 failed requests
5th percentile: 1.3414310932159423
10th percentile: 1.4335690975189208
20th percentile: 1.617845106124878
30th percentile: 1.7109275817871095
40th percentile: 1.7128165245056153
50th percentile: 1.714705467224121
60th percentile: 1.714908981323242
70th percentile: 1.7151124954223633
80th percentile: 1.8588487148284913
90th percentile: 2.146117639541626
95th percentile: 2.289752101898193
99th percentile: 2.404659671783447
mean time: 1.764516496658325
Pipeline stage StressChecker completed in 10.09s
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 0.66s
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 0.60s
Shutdown handler de-registered
chaiml-mn24b-v2preferwin_4431_v2 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 2767.07s
Shutdown handler de-registered
chaiml-mn24b-v2preferwin_4431_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwin_4431_v2 status is now torndown due to DeploymentManager action