developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwi_47511_v4
model_name: chaiml-mn24b-v2preferwi_47511_v4
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-23T17:43:39+00:00
num_battles: 5696
num_wins: 2932
celo_rating: 1279.0
family_friendly_score: 0.5571999999999999
family_friendly_standard_error: 0.007024644617345421
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune6
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': 0.5502458348799294, 'latency_mean': 1.8172723305225373, 'latency_p50': 1.8200469017028809, 'latency_p90': 2.01825807094574}, {'batch_size': 3, 'throughput': 1.1067923799147048, 'latency_mean': 2.7011308777332306, 'latency_p50': 2.7036598920822144, 'latency_p90': 3.000014400482178}, {'batch_size': 5, 'throughput': 1.4175460559279027, 'latency_mean': 3.512481071949005, 'latency_p50': 3.527914524078369, 'latency_p90': 3.9258163928985597}, {'batch_size': 6, 'throughput': 1.5173004846996818, 'latency_mean': 3.9214705991744996, 'latency_p50': 3.925387740135193, 'latency_p90': 4.474526500701904}, {'batch_size': 8, 'throughput': 1.6670946551081733, 'latency_mean': 4.777327626943588, 'latency_p50': 4.7684807777404785, 'latency_p90': 5.482597684860229}, {'batch_size': 10, 'throughput': 1.7292312487451202, 'latency_mean': 5.732910553216934, 'latency_p50': 5.752764821052551, 'latency_p90': 6.456985330581665}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwi_47511_v4
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune6
model_size: 24B
ranking_group: single
throughput_3p7s: 1.48
us_pacific_date: 2025-09-23
win_ratio: 0.514747191011236
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-47511-v4-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwi-47511-v4-mkmlizer to finish
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: Downloaded to shared memory in 49.568s
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune6 already exists in ChaiML
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpp_28lnjt, device:0
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: quantized model in 289.087s
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune6 in 338.656s
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47511-v4/nvidia
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47511-v4/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47511-v4/nvidia/config.json
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47511-v4/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47511-v4/nvidia/tokenizer.json
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47511-v4/nvidia/flywheel_model.1.safetensors
chaiml-mn24b-v2preferwi-47511-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-47511-v4/nvidia/flywheel_model.0.safetensors
Job chaiml-mn24b-v2preferwi-47511-v4-mkmlizer completed after 441.03s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwi-47511-v4-mkmlizer
Pipeline stage MKMLizer completed in 441.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mn24b-v2preferwi-47511-v4
Waiting for inference service chaiml-mn24b-v2preferwi-47511-v4 to be ready
Inference service chaiml-mn24b-v2preferwi-47511-v4 ready after 60.36900496482849s
Pipeline stage MKMLDeployer completed in 61.73s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9571752548217773s
Received healthy response to inference request in 1.9186561107635498s
Received healthy response to inference request in 3.103394031524658s
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Received healthy response to inference request in 1.9211726188659668s
Received healthy response to inference request in 1.7989931106567383s
5 requests
0 failed requests
5th percentile: 1.8229257106781005
10th percentile: 1.846858310699463
20th percentile: 1.8947235107421876
30th percentile: 1.9191594123840332
40th percentile: 1.920166015625
50th percentile: 1.9211726188659668
60th percentile: 1.935573673248291
70th percentile: 1.9499747276306152
80th percentile: 2.1864190101623535
90th percentile: 2.644906520843506
95th percentile: 2.874150276184082
99th percentile: 3.057545280456543
mean time: 2.1398782253265383
Pipeline stage StressChecker completed in 12.11s
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 1.22s
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 0.67s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_47511_v4 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mn24b-v2preferwi-47511-v4-profiler
Waiting for inference service chaiml-mn24b-v2preferwi-47511-v4-profiler to be ready
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 2804.58s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_47511_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwi_47511_v4 status is now torndown due to DeploymentManager action