developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn12b-v2preferwi_36096_v3
model_name: chaiml-mn12b-v2preferwi_36096_v3
model_group: ChaiML/mn12b_v2preferwin
status: torndown
timestamp: 2025-09-11T13:26:15+00:00
num_battles: 5810
num_wins: 3159
celo_rating: 1279.52
family_friendly_score: 0.5514
family_friendly_standard_error: 0.007033605618742069
submission_type: basic
model_repo: ChaiML/mn12b_v2preferwin1syn1_tune3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.9325304450178535, 'latency_mean': 1.0722475445270538, 'latency_p50': 1.0703439712524414, 'latency_p90': 1.1948488473892211}, {'batch_size': 5, 'throughput': 2.4711927183223596, 'latency_mean': 2.0167590618133544, 'latency_p50': 2.028604507446289, 'latency_p90': 2.295137906074524}, {'batch_size': 10, 'throughput': 3.1203379195603644, 'latency_mean': 3.1763972353935244, 'latency_p50': 3.174322247505188, 'latency_p90': 3.636591076850891}, {'batch_size': 15, 'throughput': 3.3530618286647877, 'latency_mean': 4.427839567661286, 'latency_p50': 4.424952983856201, 'latency_p90': 5.112412452697754}, {'batch_size': 20, 'throughput': 3.3680205067550317, 'latency_mean': 5.834672328233719, 'latency_p50': 5.915553092956543, 'latency_p90': 6.626904892921448}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn12b-v2preferwi_36096_v3
ineligible_reason: num_battles<10000
is_internal_developer: False
language_model: ChaiML/mn12b_v2preferwin1syn1_tune3
model_size: 13B
ranking_group: single
throughput_3p7s: 3.27
us_pacific_date: 2025-09-11
win_ratio: 0.5437177280550775
generation_params: {'temperature': 0.9, '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': '{prompt}\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-mn12b-v2preferwi-36096-v3-mkmlizer
Waiting for job on chaiml-mn12b-v2preferwi-36096-v3-mkmlizer to finish
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║                                                                     ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║                                                                     ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║                                                                     ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║                                                                     ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ║                                                                     ║
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: Downloaded to shared memory in 25.706s
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: Checking if ChaiML/mn12b_v2preferwin1syn1_tune3 already exists in ChaiML
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp2unwq_a8, device:0
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: quantized model in 146.800s
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: Processed model ChaiML/mn12b_v2preferwin1syn1_tune3 in 172.507s
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn12b-v2preferwi-36096-v3/nvidia
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn12b-v2preferwi-36096-v3/nvidia/config.json
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn12b-v2preferwi-36096-v3/nvidia/special_tokens_map.json
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn12b-v2preferwi-36096-v3/nvidia/tokenizer_config.json
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mn12b-v2preferwi-36096-v3/nvidia/tokenizer.json
chaiml-mn12b-v2preferwi-36096-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn12b-v2preferwi-36096-v3/nvidia/flywheel_model.0.safetensors
Job chaiml-mn12b-v2preferwi-36096-v3-mkmlizer completed after 226.56s with status: succeeded
Stopping job with name chaiml-mn12b-v2preferwi-36096-v3-mkmlizer
Pipeline stage MKMLizer completed in 226.95s
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-mn12b-v2preferwi-36096-v3
Waiting for inference service chaiml-mn12b-v2preferwi-36096-v3 to be ready
Inference service chaiml-mn12b-v2preferwi-36096-v3 ready after 70.16611862182617s
Pipeline stage MKMLDeployer completed in 70.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4519810676574707s
Received healthy response to inference request in 1.5729122161865234s
Received healthy response to inference request in 1.3372902870178223s
Received healthy response to inference request in 1.4690947532653809s
Received healthy response to inference request in 1.5157556533813477s
5 requests
0 failed requests
5th percentile: 1.3602284431457519
10th percentile: 1.3831665992736817
20th percentile: 1.429042911529541
30th percentile: 1.4554038047790527
40th percentile: 1.4622492790222168
50th percentile: 1.4690947532653809
60th percentile: 1.4877591133117676
70th percentile: 1.5064234733581543
80th percentile: 1.527186965942383
90th percentile: 1.5500495910644532
95th percentile: 1.5614809036254882
99th percentile: 1.5706259536743163
mean time: 1.469406795501709
Pipeline stage StressChecker completed in 8.51s
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 1.02s
Shutdown handler de-registered
chaiml-mn12b-v2preferwi_36096_v3 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 2222.14s
Shutdown handler de-registered
chaiml-mn12b-v2preferwi_36096_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn12b-v2preferwi_36096_v3 status is now torndown due to DeploymentManager action