developer_uid: AlexCuadron
submission_id: alexcuadron-chai-sft-12b_v2
model_name: alexcuadron-chai-sft-12b_v2
model_group: AlexCuadron/chai-sft-12b
status: torndown
timestamp: 2025-03-12T20:02:20+00:00
num_battles: 7688
num_wins: 3479
celo_rating: 1246.51
family_friendly_score: 0.6036
family_friendly_standard_error: 0.006917615774238983
submission_type: basic
model_repo: AlexCuadron/chai-sft-12b
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6076543043573117, 'latency_mean': 1.6455971157550813, 'latency_p50': 1.6523480415344238, 'latency_p90': 1.808163833618164}, {'batch_size': 3, 'throughput': 1.1209109505233483, 'latency_mean': 2.6683903419971466, 'latency_p50': 2.670997142791748, 'latency_p90': 2.925818371772766}, {'batch_size': 5, 'throughput': 1.3568089053420436, 'latency_mean': 3.6599256312847137, 'latency_p50': 3.6836225986480713, 'latency_p90': 4.039555859565735}, {'batch_size': 6, 'throughput': 1.3998193199195095, 'latency_mean': 4.256505570411682, 'latency_p50': 4.269383549690247, 'latency_p90': 4.774511694908142}, {'batch_size': 8, 'throughput': 1.4756830789831568, 'latency_mean': 5.377737920284272, 'latency_p50': 5.39687442779541, 'latency_p90': 5.995716452598572}, {'batch_size': 10, 'throughput': 1.5219595754960773, 'latency_mean': 6.525136512517929, 'latency_p50': 6.516802549362183, 'latency_p90': 7.419238829612731}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: alexcuadron-chai-sft-12b_v2
is_internal_developer: False
language_model: AlexCuadron/chai-sft-12b
model_size: 13B
ranking_group: single
throughput_3p7s: 1.37
us_pacific_date: 2025-03-12
win_ratio: 0.45252341311134237
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 alexcuadron-chai-sft-12b-v2-mkmlizer
Waiting for job on alexcuadron-chai-sft-12b-v2-mkmlizer to finish
alexcuadron-chai-sft-12b-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
alexcuadron-chai-sft-12b-v2-mkmlizer: ║     _____            __           __                                ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║       /___/                                                         ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║  https://mk1.ai                                                     ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║  belonging to:                                                      ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║  Chai Research Corp.                                                ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ║                                                                     ║
alexcuadron-chai-sft-12b-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
alexcuadron-chai-sft-12b-v2-mkmlizer: Downloaded to shared memory in 43.408s
alexcuadron-chai-sft-12b-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3yomja88, device:0
alexcuadron-chai-sft-12b-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
alexcuadron-chai-sft-12b-v2-mkmlizer: quantized model in 37.088s
alexcuadron-chai-sft-12b-v2-mkmlizer: Processed model AlexCuadron/chai-sft-12b in 80.497s
alexcuadron-chai-sft-12b-v2-mkmlizer: creating bucket guanaco-mkml-models
alexcuadron-chai-sft-12b-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
alexcuadron-chai-sft-12b-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v2
alexcuadron-chai-sft-12b-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v2/config.json
alexcuadron-chai-sft-12b-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v2/special_tokens_map.json
alexcuadron-chai-sft-12b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v2/tokenizer_config.json
alexcuadron-chai-sft-12b-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/alexcuadron-chai-sft-12b-v2/tokenizer.json
Job alexcuadron-chai-sft-12b-v2-mkmlizer completed after 118.77s with status: succeeded
Stopping job with name alexcuadron-chai-sft-12b-v2-mkmlizer
Pipeline stage MKMLizer completed in 119.25s
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 alexcuadron-chai-sft-12b-v2
Waiting for inference service alexcuadron-chai-sft-12b-v2 to be ready
Inference service alexcuadron-chai-sft-12b-v2 ready after 100.39742755889893s
Pipeline stage MKMLDeployer completed in 101.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.422133445739746s
Received healthy response to inference request in 1.7661912441253662s
Received healthy response to inference request in 1.4967784881591797s
Received healthy response to inference request in 1.489901065826416s
Received healthy response to inference request in 0.9962208271026611s
5 requests
0 failed requests
5th percentile: 1.094956874847412
10th percentile: 1.193692922592163
20th percentile: 1.391165018081665
30th percentile: 1.4912765502929688
40th percentile: 1.4940275192260741
50th percentile: 1.4967784881591797
60th percentile: 1.6045435905456542
70th percentile: 1.712308692932129
80th percentile: 1.8973796844482422
90th percentile: 2.159756565093994
95th percentile: 2.29094500541687
99th percentile: 2.395895757675171
mean time: 1.634245014190674
Pipeline stage StressChecker completed in 9.66s
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 0.91s
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
alexcuadron-chai-sft-12b_v2 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service alexcuadron-chai-sft-12b-v2-profiler
Waiting for inference service alexcuadron-chai-sft-12b-v2-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4420.71s
Shutdown handler de-registered
alexcuadron-chai-sft-12b_v2 status is now inactive due to auto deactivation removed underperforming models
alexcuadron-chai-sft-12b_v2 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1