developer_uid: huohuo12
submission_id: sao10k-l3-8b-lunaris-v1_v5
model_name: sao10k-l3-8b-lunaris-v1_v5
model_group: Sao10K/L3-8B-Lunaris-v1
status: torndown
timestamp: 2025-02-20T06:24:35+00:00
num_battles: 5175
num_wins: 2427
celo_rating: 1227.41
family_friendly_score: 0.5798
family_friendly_standard_error: 0.006980429213164474
submission_type: basic
model_repo: Sao10K/L3-8B-Lunaris-v1
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8444655609960745, 'latency_mean': 1.1841155683994293, 'latency_p50': 1.1855120658874512, 'latency_p90': 1.3067863225936889}, {'batch_size': 4, 'throughput': 1.7794665806350853, 'latency_mean': 2.2354383409023284, 'latency_p50': 2.2245386838912964, 'latency_p90': 2.480915570259094}, {'batch_size': 5, 'throughput': 1.9220183201306913, 'latency_mean': 2.5848922216892243, 'latency_p50': 2.6059839725494385, 'latency_p90': 2.8732274293899533}, {'batch_size': 8, 'throughput': 2.1202970137816495, 'latency_mean': 3.7503953945636748, 'latency_p50': 3.785968780517578, 'latency_p90': 4.249456286430359}, {'batch_size': 10, 'throughput': 2.1855655178733406, 'latency_mean': 4.542600138187408, 'latency_p50': 4.501336932182312, 'latency_p90': 5.166553854942322}, {'batch_size': 12, 'throughput': 2.217204101369589, 'latency_mean': 5.366018310785294, 'latency_p50': 5.345006585121155, 'latency_p90': 6.112765312194824}, {'batch_size': 15, 'throughput': 2.232845451060849, 'latency_mean': 6.635294320583344, 'latency_p50': 6.6651850938797, 'latency_p90': 7.503646945953369}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sao10k-l3-8b-lunaris-v1_v5
is_internal_developer: False
language_model: Sao10K/L3-8B-Lunaris-v1
model_size: 8B
ranking_group: single
throughput_3p7s: 2.13
us_pacific_date: 2025-02-19
win_ratio: 0.46898550724637683
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 sao10k-l3-8b-lunaris-v1-v5-mkmlizer
Waiting for job on sao10k-l3-8b-lunaris-v1-v5-mkmlizer to finish
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ _____ __ __ ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ /___/ ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ Version: 0.12.8 ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ https://mk1.ai ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ belonging to: ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ Chai Research Corp. ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ║ ║
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: Downloaded to shared memory in 31.942s
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy0w4j3fk, device:0
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: quantized model in 29.082s
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: Processed model Sao10K/L3-8B-Lunaris-v1 in 61.025s
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v5
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v5/config.json
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v5/special_tokens_map.json
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v5/tokenizer_config.json
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v5/flywheel_model.0.safetensors
sao10k-l3-8b-lunaris-v1-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:47, 2.45s/it] Loading 0: 2%|▏ | 6/291 [00:05<03:09, 1.50it/s] Loading 0: 4%|▍ | 11/291 [00:05<01:23, 3.33it/s] Loading 0: 5%|▌ | 15/291 [00:05<00:53, 5.13it/s] Loading 0: 8%|▊ | 22/291 [00:05<00:28, 9.40it/s] Loading 0: 9%|▉ | 27/291 [00:05<00:20, 12.67it/s] Loading 0: 11%|█ | 32/291 [00:05<00:15, 16.28it/s] Loading 0: 13%|█▎ | 37/291 [00:05<00:12, 20.32it/s] Loading 0: 14%|█▍ | 42/291 [00:06<00:11, 21.01it/s] Loading 0: 17%|█▋ | 49/291 [00:06<00:08, 27.95it/s] Loading 0: 19%|█▊ | 54/291 [00:06<00:07, 30.32it/s] Loading 0: 20%|██ | 59/291 [00:06<00:07, 32.00it/s] Loading 0: 22%|██▏ | 64/291 [00:06<00:09, 23.30it/s] Loading 0: 23%|██▎ | 68/291 [00:06<00:08, 24.91it/s] Loading 0: 25%|██▍ | 72/291 [00:06<00:08, 26.98it/s] Loading 0: 26%|██▌ | 76/291 [00:07<00:07, 29.06it/s] Loading 0: 27%|██▋ | 80/291 [00:07<00:07, 29.92it/s] Loading 0: 29%|██▉ | 85/291 [00:07<00:06, 32.79it/s] Loading 0: 31%|███ | 89/291 [00:07<00:06, 32.38it/s] Loading 0: 32%|███▏ | 94/291 [00:07<00:05, 35.42it/s] Loading 0: 34%|███▎ | 98/291 [00:07<00:05, 34.86it/s] Loading 0: 35%|███▌ | 102/291 [00:07<00:05, 35.86it/s] Loading 0: 36%|███▋ | 106/291 [00:07<00:05, 32.24it/s] Loading 0: 38%|███▊ | 112/291 [00:08<00:04, 37.60it/s] Loading 0: 40%|███▉ | 116/291 [00:08<00:04, 35.60it/s] Loading 0: 42%|████▏ | 121/291 [00:08<00:04, 37.98it/s] Loading 0: 43%|████▎ | 125/291 [00:08<00:04, 36.80it/s] Loading 0: 45%|████▍ | 130/291 [00:08<00:04, 39.15it/s] Loading 0: 46%|████▌ | 134/291 [00:08<00:04, 36.88it/s] Loading 0: 48%|████▊ | 139/291 [00:08<00:03, 38.94it/s] Loading 0: 49%|████▉ | 143/291 [00:08<00:03, 37.32it/s] Loading 0: 51%|█████ | 148/291 [00:09<00:03, 39.15it/s] Loading 0: 52%|█████▏ | 152/291 [00:09<00:03, 37.09it/s] Loading 0: 54%|█████▍ | 157/291 [00:09<00:03, 39.13it/s] Loading 0: 55%|█████▌ | 161/291 [00:09<00:03, 36.98it/s] Loading 0: 57%|█████▋ | 166/291 [00:09<00:05, 24.73it/s] Loading 0: 58%|█████▊ | 170/291 [00:09<00:04, 25.77it/s] Loading 0: 60%|█████▉ | 174/291 [00:09<00:04, 28.55it/s] Loading 0: 61%|██████ | 178/291 [00:10<00:04, 28.10it/s] Loading 0: 63%|██████▎ | 182/291 [00:10<00:03, 30.45it/s] Loading 0: 64%|██████▍ | 186/291 [00:10<00:03, 29.68it/s] Loading 0: 66%|██████▌ | 191/291 [00:10<00:02, 34.24it/s] Loading 0: 67%|██████▋ | 195/291 [00:10<00:02, 32.28it/s] Loading 0: 69%|██████▊ | 200/291 [00:10<00:02, 36.41it/s] Loading 0: 70%|███████ | 204/291 [00:10<00:02, 33.24it/s] Loading 0: 72%|███████▏ | 209/291 [00:10<00:02, 36.82it/s] Loading 0: 73%|███████▎ | 213/291 [00:11<00:02, 33.79it/s] Loading 0: 75%|███████▍ | 218/291 [00:11<00:01, 37.44it/s] Loading 0: 76%|███████▋ | 222/291 [00:11<00:02, 34.04it/s] Loading 0: 78%|███████▊ | 227/291 [00:11<00:01, 37.78it/s] Loading 0: 79%|███████▉ | 231/291 [00:11<00:01, 34.67it/s] Loading 0: 81%|████████▏ | 237/291 [00:11<00:01, 41.03it/s] Loading 0: 83%|████████▎ | 242/291 [00:11<00:01, 38.89it/s] Loading 0: 85%|████████▍ | 247/291 [00:11<00:01, 40.34it/s] Loading 0: 87%|████████▋ | 252/291 [00:12<00:00, 39.87it/s] Loading 0: 88%|████████▊ | 257/291 [00:12<00:00, 38.90it/s] Loading 0: 90%|████████▉ | 261/291 [00:12<00:00, 37.70it/s] Loading 0: 91%|█████████ | 265/291 [00:12<00:00, 36.92it/s] Loading 0: 92%|█████████▏| 269/291 [00:12<00:00, 23.15it/s] Loading 0: 94%|█████████▍| 274/291 [00:12<00:00, 27.26it/s] Loading 0: 96%|█████████▌| 278/291 [00:13<00:00, 28.17it/s] Loading 0: 97%|█████████▋| 283/291 [00:13<00:00, 31.77it/s] Loading 0: 99%|█████████▊| 287/291 [00:13<00:00, 31.75it/s] Loading 0: 100%|██████████| 291/291 [00:13<00:00, 33.29it/s]
Job sao10k-l3-8b-lunaris-v1-v5-mkmlizer completed after 83.48s with status: succeeded
Stopping job with name sao10k-l3-8b-lunaris-v1-v5-mkmlizer
Pipeline stage MKMLizer completed in 83.94s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-l3-8b-lunaris-v1-v5
Waiting for inference service sao10k-l3-8b-lunaris-v1-v5 to be ready
Inference service sao10k-l3-8b-lunaris-v1-v5 ready after 191.11398673057556s
Pipeline stage MKMLDeployer completed in 191.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9309818744659424s
Received healthy response to inference request in 1.5360512733459473s
Received healthy response to inference request in 1.3396470546722412s
Received healthy response to inference request in 1.2514550685882568s
Received healthy response to inference request in 1.175015926361084s
5 requests
0 failed requests
5th percentile: 1.1903037548065185
10th percentile: 1.205591583251953
20th percentile: 1.2361672401428223
30th percentile: 1.2690934658050537
40th percentile: 1.3043702602386475
50th percentile: 1.3396470546722412
60th percentile: 1.4182087421417235
70th percentile: 1.496770429611206
80th percentile: 1.6150373935699465
90th percentile: 1.7730096340179444
95th percentile: 1.8519957542419432
99th percentile: 1.9151846504211425
mean time: 1.4466302394866943
Pipeline stage StressChecker completed in 8.34s
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 0.60s
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 0.60s
Shutdown handler de-registered
sao10k-l3-8b-lunaris-v1_v5 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 0.09s
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 sao10k-l3-8b-lunaris-v1-v5-profiler
Waiting for inference service sao10k-l3-8b-lunaris-v1-v5-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 2370.08s
Shutdown handler de-registered
sao10k-l3-8b-lunaris-v1_v5 status is now inactive due to auto deactivation removed underperforming models
sao10k-l3-8b-lunaris-v1_v5 status is now torndown due to DeploymentManager action
sao10k-l3-8b-lunaris-v1_v5 status is now torndown due to DeploymentManager action
sao10k-l3-8b-lunaris-v1_v5 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1