developer_uid: zonemercy
submission_id: chaiml-2a6f-6970-linear-w01_v3
model_name: chaiml-2a6f-6970-linear-w01_v3
model_group: ChaiML/2a6f-6970-linear-
status: torndown
timestamp: 2025-10-05T19:20:47+00:00
num_battles: 5773
num_wins: 2908
celo_rating: 1291.94
family_friendly_score: 0.5322
family_friendly_standard_error: 0.007056389445034904
submission_type: basic
model_repo: ChaiML/2a6f-6970-linear-w01
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': 0.547963016807636, 'latency_mean': 1.8248136472702026, 'latency_p50': 1.8209936618804932, 'latency_p90': 2.026190686225891}, {'batch_size': 3, 'throughput': 1.103600484133965, 'latency_mean': 2.706626054048538, 'latency_p50': 2.6984174251556396, 'latency_p90': 3.0883625030517576}, {'batch_size': 5, 'throughput': 1.4187890535855765, 'latency_mean': 3.5083724701404573, 'latency_p50': 3.498471975326538, 'latency_p90': 3.8765686988830566}, {'batch_size': 6, 'throughput': 1.5325704153463562, 'latency_mean': 3.8869755160808563, 'latency_p50': 3.8924461603164673, 'latency_p90': 4.523128890991211}, {'batch_size': 8, 'throughput': 1.673971505422635, 'latency_mean': 4.747621613740921, 'latency_p50': 4.740090012550354, 'latency_p90': 5.378489136695862}, {'batch_size': 10, 'throughput': 1.7606450115988146, 'latency_mean': 5.6529816162586215, 'latency_p50': 5.588117003440857, 'latency_p90': 6.454317188262939}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-2a6f-6970-linear-w01_v3
is_internal_developer: True
language_model: ChaiML/2a6f-6970-linear-w01
model_size: 24B
ranking_group: single
throughput_3p7s: 1.49
us_pacific_date: 2025-10-05
win_ratio: 0.5037242335007794
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['</s>', '\n', 'You:', '###'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
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-2a6f-6970-linear-w01-v3-mkmlizer
Waiting for job on chaiml-2a6f-6970-linear-w01-v3-mkmlizer to finish
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-2a6f-6970-linear-w01-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║                                                                     ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║                                                                     ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║                                                                     ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║                                                                     ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ║                                                                     ║
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: Downloaded to shared memory in 49.503s
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: Checking if ChaiML/2a6f-6970-linear-w01 already exists in ChaiML
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmphst34nz5, device:0
chaiml-2a6f-6970-linear-w01-v3-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-2a6f-6970-linear-w01-v3-mkmlizer: quantized model in 279.822s
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: Processed model ChaiML/2a6f-6970-linear-w01 in 329.325s
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w01-v3/nvidia
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w01-v3/nvidia/config.json
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w01-v3/nvidia/special_tokens_map.json
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w01-v3/nvidia/tokenizer_config.json
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w01-v3/nvidia/tokenizer.json
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w01-v3/nvidia/flywheel_model.1.safetensors
chaiml-2a6f-6970-linear-w01-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-2a6f-6970-linear-w01-v3/nvidia/flywheel_model.0.safetensors
Job chaiml-2a6f-6970-linear-w01-v3-mkmlizer completed after 457.76s with status: succeeded
Stopping job with name chaiml-2a6f-6970-linear-w01-v3-mkmlizer
Pipeline stage MKMLizer completed in 458.31s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-2a6f-6970-linear-w01-v3
Waiting for inference service chaiml-2a6f-6970-linear-w01-v3 to be ready
Inference service chaiml-2a6f-6970-linear-w01-v3 ready after 40.206804275512695s
Pipeline stage MKMLDeployer completed in 40.76s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.587266445159912s
Received healthy response to inference request in 2.2244460582733154s
Received healthy response to inference request in 2.284785747528076s
Received healthy response to inference request in 1.6506459712982178s
Received healthy response to inference request in 1.9521808624267578s
5 requests
0 failed requests
5th percentile: 1.7109529495239257
10th percentile: 1.7712599277496337
20th percentile: 1.8918738842010498
30th percentile: 2.0066339015960692
40th percentile: 2.1155399799346926
50th percentile: 2.2244460582733154
60th percentile: 2.2485819339752195
70th percentile: 2.272717809677124
80th percentile: 2.3452818870544436
90th percentile: 2.4662741661071776
95th percentile: 2.5267703056335447
99th percentile: 2.5751672172546387
mean time: 2.139865016937256
Pipeline stage StressChecker completed in 11.94s
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 0.65s
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 0.94s
Shutdown handler de-registered
chaiml-2a6f-6970-linear-w01_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-2a6f-6970-linear-w01-v3-profiler
Waiting for inference service chaiml-2a6f-6970-linear-w01-v3-profiler to be ready
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 2897.28s
Shutdown handler de-registered
chaiml-2a6f-6970-linear-w01_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-2a6f-6970-linear-w01_v3 status is now torndown due to DeploymentManager action