developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwi_18626_v5
model_name: chaiml-mn24b-v2preferwi_18626_v5
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-23T17:23:20+00:00
num_battles: 5729
num_wins: 2901
celo_rating: 1267.29
family_friendly_score: 0.5558000000000001
family_friendly_standard_error: 0.0070268963276826565
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune1
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': 0.5526938463516803, 'latency_mean': 1.8092089474201203, 'latency_p50': 1.7931605577468872, 'latency_p90': 2.0162708282470705}, {'batch_size': 3, 'throughput': 1.1065963589890726, 'latency_mean': 2.7053430998325347, 'latency_p50': 2.681753635406494, 'latency_p90': 3.0870028734207153}, {'batch_size': 5, 'throughput': 1.418751442654268, 'latency_mean': 3.5090800750255586, 'latency_p50': 3.522662043571472, 'latency_p90': 3.9399624347686766}, {'batch_size': 6, 'throughput': 1.5287795658990404, 'latency_mean': 3.9065409326553344, 'latency_p50': 3.8823797702789307, 'latency_p90': 4.487026643753052}, {'batch_size': 8, 'throughput': 1.6870601493767396, 'latency_mean': 4.704438022375107, 'latency_p50': 4.688404560089111, 'latency_p90': 5.382610201835632}, {'batch_size': 10, 'throughput': 1.7701769246952797, 'latency_mean': 5.5991974496841435, 'latency_p50': 5.557414650917053, 'latency_p90': 6.428155016899109}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwi_18626_v5
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune1
model_size: 24B
ranking_group: single
throughput_3p7s: 1.48
us_pacific_date: 2025-09-23
win_ratio: 0.506371094431838
generation_params: {'temperature': 0.8, '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-18626-v5-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwi-18626-v5-mkmlizer to finish
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: Downloaded to shared memory in 47.863s
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune1 already exists in ChaiML
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpn4nrj51p, device:0
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: quantized model in 286.672s
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune1 in 334.535s
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-18626-v5/nvidia
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-18626-v5/nvidia/config.json
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-18626-v5/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-18626-v5/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-18626-v5/nvidia/flywheel_model.1.safetensors
chaiml-mn24b-v2preferwi-18626-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-18626-v5/nvidia/flywheel_model.0.safetensors
Job chaiml-mn24b-v2preferwi-18626-v5-mkmlizer completed after 510.85s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwi-18626-v5-mkmlizer
Pipeline stage MKMLizer completed in 511.31s
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-mn24b-v2preferwi-18626-v5
Waiting for inference service chaiml-mn24b-v2preferwi-18626-v5 to be ready
Inference service chaiml-mn24b-v2preferwi-18626-v5 ready after 50.25892734527588s
Pipeline stage MKMLDeployer completed in 51.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1121301651000977s
Received healthy response to inference request in 2.072690725326538s
Received healthy response to inference request in 2.233827829360962s
Received healthy response to inference request in 2.265284538269043s
Received healthy response to inference request in 2.2183611392974854s
5 requests
0 failed requests
5th percentile: 2.08057861328125
10th percentile: 2.088466501235962
20th percentile: 2.104242277145386
30th percentile: 2.133376359939575
40th percentile: 2.1758687496185303
50th percentile: 2.2183611392974854
60th percentile: 2.224547815322876
70th percentile: 2.2307344913482665
80th percentile: 2.2401191711425783
90th percentile: 2.2527018547058106
95th percentile: 2.2589931964874266
99th percentile: 2.2640262699127196
mean time: 2.1804588794708253
Pipeline stage StressChecker completed in 12.79s
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 0.65s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_18626_v5 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 2902.63s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_18626_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwi_18626_v5 status is now torndown due to DeploymentManager action