developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwi_59255_v2
model_name: chaiml-mn24b-v2preferwi_59255_v2
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-23T17:44:29+00:00
num_battles: 5608
num_wins: 2893
celo_rating: 1271.95
family_friendly_score: 0.5548
family_friendly_standard_error: 0.007028470103799261
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune7
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': 0.5508804603425557, 'latency_mean': 1.815149894952774, 'latency_p50': 1.811894178390503, 'latency_p90': 2.0143512964248655}, {'batch_size': 3, 'throughput': 1.1167826412901398, 'latency_mean': 2.681704367399216, 'latency_p50': 2.6865577697753906, 'latency_p90': 2.942769360542297}, {'batch_size': 5, 'throughput': 1.4453753676103427, 'latency_mean': 3.4499391329288485, 'latency_p50': 3.4415751695632935, 'latency_p90': 3.895951199531555}, {'batch_size': 6, 'throughput': 1.5379182883595544, 'latency_mean': 3.8768182337284087, 'latency_p50': 3.9011950492858887, 'latency_p90': 4.385343384742737}, {'batch_size': 8, 'throughput': 1.7158669173284444, 'latency_mean': 4.624512677192688, 'latency_p50': 4.582302451133728, 'latency_p90': 5.337947487831116}, {'batch_size': 10, 'throughput': 1.783824319632093, 'latency_mean': 5.563611526489257, 'latency_p50': 5.5643147230148315, 'latency_p90': 6.278490877151489}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwi_59255_v2
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune7
model_size: 24B
ranking_group: single
throughput_3p7s: 1.51
us_pacific_date: 2025-09-23
win_ratio: 0.515870185449358
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-v2preferwi-59255-v2-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwi-59255-v2-mkmlizer to finish
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ Version: 0.30.2 ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ belonging to: ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ║ ║
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: Downloaded to shared memory in 55.618s
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune7 already exists in ChaiML
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpu5dd9cj_, device:0
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-59255-v2-mkmlizer: quantized model in 289.742s
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_nonl_bo1_tune7 in 345.360s
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-59255-v2/nvidia
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-59255-v2/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-59255-v2/nvidia/config.json
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-59255-v2/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-59255-v2/nvidia/tokenizer.json
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-59255-v2/nvidia/flywheel_model.1.safetensors
chaiml-mn24b-v2preferwi-59255-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-59255-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-mn24b-v2preferwi-59255-v2-mkmlizer completed after 470.76s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwi-59255-v2-mkmlizer
Pipeline stage MKMLizer completed in 471.25s
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-v2preferwi-59255-v2
Waiting for inference service chaiml-mn24b-v2preferwi-59255-v2 to be ready
Inference service chaiml-mn24b-v2preferwi-59255-v2 ready after 60.469266414642334s
Pipeline stage MKMLDeployer completed in 61.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0152764320373535s
Received healthy response to inference request in 1.9090650081634521s
Received healthy response to inference request in 1.8472206592559814s
Received healthy response to inference request in 2.4531874656677246s
Received healthy response to inference request in 1.8311822414398193s
5 requests
0 failed requests
5th percentile: 1.8343899250030518
10th percentile: 1.8375976085662842
20th percentile: 1.844012975692749
30th percentile: 1.8595895290374755
40th percentile: 1.884327268600464
50th percentile: 1.9090650081634521
60th percentile: 1.9515495777130127
70th percentile: 1.9940341472625733
80th percentile: 2.102858638763428
90th percentile: 2.278023052215576
95th percentile: 2.3656052589416503
99th percentile: 2.43567102432251
mean time: 2.011186361312866
Pipeline stage StressChecker completed in 11.35s
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 0.63s
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_59255_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 2824.77s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_59255_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwi_59255_v2 status is now torndown due to DeploymentManager action