developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwin_3050_v8
model_name: chaiml-mn24b-v2preferwin_3050_v8
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-13T19:19:26+00:00
num_battles: 6390
num_wins: 3461
celo_rating: 1279.8
family_friendly_score: 0.5813999999999999
family_friendly_standard_error: 0.006976733333014814
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin1syn1_tune16
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': 0.544435447588998, 'latency_mean': 1.8366654098033905, 'latency_p50': 1.8278447389602661, 'latency_p90': 2.0344734668731688}, {'batch_size': 3, 'throughput': 1.10224466038847, 'latency_mean': 2.7201527845859528, 'latency_p50': 2.728306531906128, 'latency_p90': 2.973753237724304}, {'batch_size': 5, 'throughput': 1.4238498544071374, 'latency_mean': 3.491004890203476, 'latency_p50': 3.480833411216736, 'latency_p90': 3.879149603843689}, {'batch_size': 6, 'throughput': 1.5264564737536699, 'latency_mean': 3.9171789753437043, 'latency_p50': 3.944911003112793, 'latency_p90': 4.394423961639404}, {'batch_size': 8, 'throughput': 1.6775991553928462, 'latency_mean': 4.732610695362091, 'latency_p50': 4.653391718864441, 'latency_p90': 5.540539693832398}, {'batch_size': 10, 'throughput': 1.7362525018474133, 'latency_mean': 5.70808770775795, 'latency_p50': 5.667234420776367, 'latency_p90': 6.5582692384719845}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwin_3050_v8
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin1syn1_tune16
model_size: 24B
ranking_group: single
throughput_3p7s: 1.48
us_pacific_date: 2025-09-13
win_ratio: 0.5416275430359937
generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.25, 'frequency_penalty': 0.25, '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-v2preferwin-3050-v8-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwin-3050-v8-mkmlizer to finish
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ Version: 0.30.2 ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ https://mk1.ai ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ belonging to: ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ Chai Research Corp. ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ║ ║
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: Downloaded to shared memory in 56.144s
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: Checking if ChaiML/mn24b_v2preferwin1syn1_tune16 already exists in ChaiML
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp_nipqeo9, device:0
chaiml-mn24b-v2preferwin-3050-v8-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', '')
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-v2preferwin-3050-v8-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-3050-v8/nvidia
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-3050-v8/nvidia/config.json
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-3050-v8/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-3050-v8/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-3050-v8/nvidia/tokenizer.json
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-3050-v8/nvidia/flywheel_model.1.safetensors
chaiml-mn24b-v2preferwin-3050-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwin-3050-v8/nvidia/flywheel_model.0.safetensors
Job chaiml-mn24b-v2preferwin-3050-v8-mkmlizer completed after 457.92s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwin-3050-v8-mkmlizer
Pipeline stage MKMLizer completed in 458.77s
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-v2preferwin-3050-v8
Waiting for inference service chaiml-mn24b-v2preferwin-3050-v8 to be ready
Inference service chaiml-mn24b-v2preferwin-3050-v8 ready after 30.19017267227173s
Pipeline stage MKMLDeployer completed in 30.71s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1289055347442627s
Received healthy response to inference request in 2.229701280593872s
Received healthy response to inference request in 2.8260555267333984s
Received healthy response to inference request in 1.815871000289917s
Received healthy response to inference request in 1.9309790134429932s
5 requests
0 failed requests
5th percentile: 1.8388926029205321
10th percentile: 1.8619142055511475
20th percentile: 1.907957410812378
30th percentile: 1.970564317703247
40th percentile: 2.049734926223755
50th percentile: 2.1289055347442627
60th percentile: 2.1692238330841063
70th percentile: 2.2095421314239503
80th percentile: 2.3489721298217776
90th percentile: 2.587513828277588
95th percentile: 2.706784677505493
99th percentile: 2.8022013568878172
mean time: 2.1863024711608885
Pipeline stage StressChecker completed in 12.05s
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 0.59s
Shutdown handler de-registered
chaiml-mn24b-v2preferwin_3050_v8 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 2730.42s
Shutdown handler de-registered
chaiml-mn24b-v2preferwin_3050_v8 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwin_3050_v8 status is now torndown due to DeploymentManager action