developer_uid: bogoconic1
submission_id: chaiml-gy-exp1-llama31-_36994_v1
model_name: chaiml-gy-exp1-llama31-_36994_v1
model_group: ChaiML/gy-exp1-llama31-8
status: torndown
timestamp: 2025-06-24T06:41:15+00:00
num_battles: 7246
num_wins: 3014
celo_rating: 1220.5
family_friendly_score: 0.6062000000000001
family_friendly_standard_error: 0.006909725899049831
submission_type: basic
model_repo: ChaiML/gy-exp1-llama31-8b-sft-full-332k-public-ep1
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8408738258720491, 'latency_mean': 1.1891130363941194, 'latency_p50': 1.188725471496582, 'latency_p90': 1.325957465171814}, {'batch_size': 4, 'throughput': 1.7156275500611005, 'latency_mean': 2.3169902288913726, 'latency_p50': 2.2986141443252563, 'latency_p90': 2.581560921669006}, {'batch_size': 5, 'throughput': 1.850848356096265, 'latency_mean': 2.687153388261795, 'latency_p50': 2.692982792854309, 'latency_p90': 2.9882344007492065}, {'batch_size': 8, 'throughput': 2.0376751755025806, 'latency_mean': 3.8881158316135407, 'latency_p50': 3.9152936935424805, 'latency_p90': 4.332923316955567}, {'batch_size': 10, 'throughput': 2.0682090686514774, 'latency_mean': 4.790266190767288, 'latency_p50': 4.81846010684967, 'latency_p90': 5.377789926528931}, {'batch_size': 12, 'throughput': 2.1150690299997748, 'latency_mean': 5.612860205173493, 'latency_p50': 5.629715323448181, 'latency_p90': 6.238384008407593}, {'batch_size': 15, 'throughput': 2.1184162813169287, 'latency_mean': 6.987836567163467, 'latency_p50': 7.026509404182434, 'latency_p90': 7.856952214241027}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: chaiml-gy-exp1-llama31-_36994_v1
is_internal_developer: True
language_model: ChaiML/gy-exp1-llama31-8b-sft-full-332k-public-ep1
model_size: 8B
ranking_group: single
throughput_3p7s: 2.04
us_pacific_date: 2025-06-23
win_ratio: 0.4159536295887386
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 chaiml-gy-exp1-llama31-36994-v1-mkmlizer
Waiting for job on chaiml-gy-exp1-llama31-36994-v1-mkmlizer to finish
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: Downloaded to shared memory in 29.875s
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: Checking if ChaiML/gy-exp1-llama31-8b-sft-full-332k-public-ep1 already exists in ChaiML
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj27ewcgd, device:0
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: quantized model in 25.125s
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: Processed model ChaiML/gy-exp1-llama31-8b-sft-full-332k-public-ep1 in 55.001s
chaiml-gy-exp1-llama31-36994-v1-mkmlizer: creating bucket guanaco-mkml-models
Job chaiml-gy-exp1-llama31-36994-v1-mkmlizer completed after 94.36s with status: succeeded
Stopping job with name chaiml-gy-exp1-llama31-36994-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.95s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp1-llama31-36994-v1
Waiting for inference service chaiml-gy-exp1-llama31-36994-v1 to be ready
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-gy-exp1-llama31-36994-v1 ready after 130.48582887649536s
Pipeline stage MKMLDeployer completed in 131.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7229316234588623s
Received healthy response to inference request in 1.160956859588623s
Received healthy response to inference request in 1.1394586563110352s
Received healthy response to inference request in 1.3690526485443115s
Received healthy response to inference request in 1.4931831359863281s
5 requests
0 failed requests
5th percentile: 1.1437582969665527
10th percentile: 1.1480579376220703
20th percentile: 1.1566572189331055
30th percentile: 1.2025760173797608
40th percentile: 1.2858143329620362
50th percentile: 1.3690526485443115
60th percentile: 1.4187048435211183
70th percentile: 1.4683570384979248
80th percentile: 1.539132833480835
90th percentile: 1.6310322284698486
95th percentile: 1.6769819259643555
99th percentile: 1.7137416839599608
mean time: 1.377116584777832
Pipeline stage StressChecker completed in 8.29s
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 0.85s
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 0.72s
Shutdown handler de-registered
chaiml-gy-exp1-llama31-_36994_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 3047.73s
Shutdown handler de-registered
chaiml-gy-exp1-llama31-_36994_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp1-llama31-_36994_v1 status is now torndown due to DeploymentManager action