developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwi_37936_v5
model_name: chaiml-mn24b-v2preferwi_37936_v5
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-18T22:18:04+00:00
num_battles: 5390
num_wins: 2817
celo_rating: 1272.02
family_friendly_score: 0.5696
family_friendly_standard_error: 0.007002225931801972
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_bo16_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': 0.5576601946070016, 'latency_mean': 1.7931063735485078, 'latency_p50': 1.7775131464004517, 'latency_p90': 1.9932376623153687}, {'batch_size': 3, 'throughput': 1.1224396163661174, 'latency_mean': 2.6693037593364717, 'latency_p50': 2.673335552215576, 'latency_p90': 2.9383373260498047}, {'batch_size': 5, 'throughput': 1.4396124750747186, 'latency_mean': 3.4473414063453673, 'latency_p50': 3.471976399421692, 'latency_p90': 3.816025638580322}, {'batch_size': 6, 'throughput': 1.5425769232117281, 'latency_mean': 3.8454348528385163, 'latency_p50': 3.8766062259674072, 'latency_p90': 4.326747941970825}, {'batch_size': 8, 'throughput': 1.700866429081013, 'latency_mean': 4.662307118177414, 'latency_p50': 4.627185106277466, 'latency_p90': 5.326450705528259}, {'batch_size': 10, 'throughput': 1.8094492912705835, 'latency_mean': 5.488388308286667, 'latency_p50': 5.503965616226196, 'latency_p90': 6.25745325088501}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwi_37936_v5
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_bo16_tune6
model_size: 24B
ranking_group: single
throughput_3p7s: 1.52
us_pacific_date: 2025-09-18
win_ratio: 0.5226345083487941
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-37936-v5-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwi-37936-v5-mkmlizer to finish
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: Downloaded to shared memory in 78.015s
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_bo16_tune6 already exists in ChaiML
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp379wfb8n, device:0
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: quantized model in 290.483s
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_bo16_tune6 in 368.498s
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-37936-v5/nvidia
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-37936-v5/nvidia/config.json
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-37936-v5/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-37936-v5/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-37936-v5/nvidia/tokenizer.json
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-37936-v5/nvidia/flywheel_model.0.safetensors
chaiml-mn24b-v2preferwi-37936-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-37936-v5/nvidia/flywheel_model.1.safetensors
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', '')
Job chaiml-mn24b-v2preferwi-37936-v5-mkmlizer completed after 422.72s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwi-37936-v5-mkmlizer
Pipeline stage MKMLizer completed in 423.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mn24b-v2preferwi-37936-v5
Waiting for inference service chaiml-mn24b-v2preferwi-37936-v5 to be ready
Inference service chaiml-mn24b-v2preferwi-37936-v5 ready after 50.238874197006226s
Pipeline stage MKMLDeployer completed in 50.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5166895389556885s
Received healthy response to inference request in 1.6820142269134521s
Received healthy response to inference request in 2.0664103031158447s
Received healthy response to inference request in 1.5702950954437256s
Received healthy response to inference request in 1.8370251655578613s
5 requests
0 failed requests
5th percentile: 1.5926389217376709
10th percentile: 1.6149827480316161
20th percentile: 1.6596704006195069
30th percentile: 1.713016414642334
40th percentile: 1.7750207901000976
50th percentile: 1.8370251655578613
60th percentile: 1.9287792205810548
70th percentile: 2.0205332756042482
80th percentile: 2.1564661502838134
90th percentile: 2.336577844619751
95th percentile: 2.42663369178772
99th percentile: 2.4986783695220947
mean time: 1.9344868659973145
Pipeline stage StressChecker completed in 10.94s
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 0.59s
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_37936_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 2973.44s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_37936_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwi_37936_v5 status is now torndown due to DeploymentManager action