developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwi_36559_v5
model_name: chaiml-mn24b-v2preferwi_36559_v5
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-17T03:26:34+00:00
num_battles: 5882
num_wins: 2999
celo_rating: 1261.29
family_friendly_score: 0.5644
family_friendly_standard_error: 0.007012169992234929
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_bo4_tune4
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': 0.5450739972788549, 'latency_mean': 1.834508159160614, 'latency_p50': 1.848215103149414, 'latency_p90': 2.021123504638672}, {'batch_size': 3, 'throughput': 1.1182666695987267, 'latency_mean': 2.6765444600582122, 'latency_p50': 2.6766449213027954, 'latency_p90': 2.99219057559967}, {'batch_size': 5, 'throughput': 1.4428201962801532, 'latency_mean': 3.4419892632961275, 'latency_p50': 3.438711643218994, 'latency_p90': 3.8711395263671875}, {'batch_size': 6, 'throughput': 1.5339997042711209, 'latency_mean': 3.888407871723175, 'latency_p50': 3.8721107244491577, 'latency_p90': 4.4393093347549435}, {'batch_size': 8, 'throughput': 1.693254456405777, 'latency_mean': 4.683459813594818, 'latency_p50': 4.71287727355957, 'latency_p90': 5.302936005592346}, {'batch_size': 10, 'throughput': 1.7840263267811727, 'latency_mean': 5.539787079095841, 'latency_p50': 5.524712443351746, 'latency_p90': 6.339050030708313}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwi_36559_v5
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_bo4_tune4
model_size: 24B
ranking_group: single
throughput_3p7s: 1.51
us_pacific_date: 2025-09-16
win_ratio: 0.5098605916354981
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-36559-v5-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwi-36559-v5-mkmlizer to finish
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: Downloaded to shared memory in 57.124s
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_bo4_tune4 already exists in ChaiML
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpli0abupa, device:0
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: quantized model in 287.679s
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_bo4_tune4 in 344.804s
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-36559-v5/nvidia
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-36559-v5/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-36559-v5/nvidia/config.json
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-36559-v5/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-36559-v5/nvidia/tokenizer.json
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', '')
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-36559-v5/nvidia/flywheel_model.1.safetensors
chaiml-mn24b-v2preferwi-36559-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-36559-v5/nvidia/flywheel_model.0.safetensors
Job chaiml-mn24b-v2preferwi-36559-v5-mkmlizer completed after 458.38s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwi-36559-v5-mkmlizer
Pipeline stage MKMLizer completed in 458.92s
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-36559-v5
Waiting for inference service chaiml-mn24b-v2preferwi-36559-v5 to be ready
Inference service chaiml-mn24b-v2preferwi-36559-v5 ready after 40.259546756744385s
Pipeline stage MKMLDeployer completed in 41.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8785288333892822s
Received healthy response to inference request in 1.7989482879638672s
Received healthy response to inference request in 1.635392665863037s
Received healthy response to inference request in 1.6064839363098145s
Received healthy response to inference request in 1.6544063091278076s
5 requests
0 failed requests
5th percentile: 1.612265682220459
10th percentile: 1.6180474281311035
20th percentile: 1.6296109199523925
30th percentile: 1.6391953945159912
40th percentile: 1.6468008518218995
50th percentile: 1.6544063091278076
60th percentile: 1.7122231006622315
70th percentile: 1.7700398921966551
80th percentile: 1.8148643970489502
90th percentile: 1.8466966152191162
95th percentile: 1.8626127243041992
99th percentile: 1.8753456115722655
mean time: 1.7147520065307618
Pipeline stage StressChecker completed in 10.04s
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 0.81s
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 0.64s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_36559_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 2704.25s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_36559_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwi_36559_v5 status is now torndown due to DeploymentManager action