developer_uid: rica40325
submission_id: rica40325-filter65k-v6-600_v1
model_name: rica40325-filter65k-v6-600_v1
model_group: rica40325/filter65k-v6-6
status: torndown
timestamp: 2025-06-21T02:44:16+00:00
num_battles: 6975
num_wins: 2748
celo_rating: 1200.86
family_friendly_score: 0.609
family_friendly_standard_error: 0.006900999927546732
submission_type: basic
model_repo: rica40325/filter65k-v6-600
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': 0.5915084152233878, 'latency_mean': 1.6904028177261352, 'latency_p50': 1.6872832775115967, 'latency_p90': 1.8567192077636718}, {'batch_size': 3, 'throughput': 1.0752410988990466, 'latency_mean': 2.7816252088546753, 'latency_p50': 2.765466809272766, 'latency_p90': 3.0590534925460817}, {'batch_size': 5, 'throughput': 1.2882366176632436, 'latency_mean': 3.8554263710975647, 'latency_p50': 3.851964235305786, 'latency_p90': 4.322427988052368}, {'batch_size': 6, 'throughput': 1.3575397954709962, 'latency_mean': 4.392961710691452, 'latency_p50': 4.404982328414917, 'latency_p90': 4.940063405036926}, {'batch_size': 8, 'throughput': 1.4229916366064366, 'latency_mean': 5.588047227859497, 'latency_p50': 5.599075794219971, 'latency_p90': 6.276355719566345}, {'batch_size': 10, 'throughput': 1.448561317386156, 'latency_mean': 6.859895944595337, 'latency_p50': 6.90092146396637, 'latency_p90': 7.688638854026794}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-filter65k-v6-600_v1
is_internal_developer: False
language_model: rica40325/filter65k-v6-600
model_size: 13B
ranking_group: single
throughput_3p7s: 1.27
us_pacific_date: 2025-06-20
win_ratio: 0.3939784946236559
generation_params: {'temperature': 1.0, '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': 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 rica40325-filter65k-v6-600-v1-mkmlizer
Waiting for job on rica40325-filter65k-v6-600-v1-mkmlizer to finish
rica40325-filter65k-v6-600-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filter65k-v6-600-v1-mkmlizer: ║                                                                     ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║                                                                     ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║                                                                     ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║                                                                     ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-filter65k-v6-600-v1-mkmlizer: ║                                                                     ║
rica40325-filter65k-v6-600-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filter65k-v6-600-v1-mkmlizer: Downloaded to shared memory in 44.531s
rica40325-filter65k-v6-600-v1-mkmlizer: Checking if rica40325/filter65k-v6-600 already exists in ChaiML
rica40325-filter65k-v6-600-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu3tuwve4, device:0
rica40325-filter65k-v6-600-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filter65k-v6-600-v1-mkmlizer: quantized model in 31.435s
rica40325-filter65k-v6-600-v1-mkmlizer: Processed model rica40325/filter65k-v6-600 in 76.051s
rica40325-filter65k-v6-600-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filter65k-v6-600-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filter65k-v6-600-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filter65k-v6-600-v1
rica40325-filter65k-v6-600-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-filter65k-v6-600-v1/config.json
rica40325-filter65k-v6-600-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filter65k-v6-600-v1/special_tokens_map.json
rica40325-filter65k-v6-600-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-filter65k-v6-600-v1/tokenizer_config.json
rica40325-filter65k-v6-600-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filter65k-v6-600-v1/tokenizer.json
rica40325-filter65k-v6-600-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filter65k-v6-600-v1/flywheel_model.0.safetensors
Job rica40325-filter65k-v6-600-v1-mkmlizer completed after 104.29s with status: succeeded
Stopping job with name rica40325-filter65k-v6-600-v1-mkmlizer
Pipeline stage MKMLizer completed in 120.13s
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 rica40325-filter65k-v6-600-v1
Waiting for inference service rica40325-filter65k-v6-600-v1 to be ready
Inference service rica40325-filter65k-v6-600-v1 ready after 120.74275875091553s
Pipeline stage MKMLDeployer completed in 121.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.606328010559082s
Received healthy response to inference request in 1.5767755508422852s
Received healthy response to inference request in 1.6809844970703125s
Received healthy response to inference request in 1.7592053413391113s
Received healthy response to inference request in 1.7530384063720703s
5 requests
0 failed requests
5th percentile: 1.5976173400878906
10th percentile: 1.618459129333496
20th percentile: 1.660142707824707
30th percentile: 1.695395278930664
40th percentile: 1.724216842651367
50th percentile: 1.7530384063720703
60th percentile: 1.7555051803588868
70th percentile: 1.757971954345703
80th percentile: 1.9286298751831057
90th percentile: 2.2674789428710938
95th percentile: 2.436903476715088
99th percentile: 2.5724431037902833
mean time: 1.8752663612365723
Pipeline stage StressChecker completed in 11.29s
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 0.66s
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
rica40325-filter65k-v6-600_v1 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 3084.29s
Shutdown handler de-registered
rica40325-filter65k-v6-600_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-filter65k-v6-600_v1 status is now torndown due to DeploymentManager action