submission_id: sao10k-hanami-1_v1
developer_uid: sao10k
alignment_samples: 13454
alignment_score: -2.086323910070695
best_of: 8
celo_rating: 1256.41
display_name: Hanami1
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '<|eot_id|>', '\n\n{user_name}', '\nYou:', '<|end_header_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Sao10K/Hanami-1
latencies: [{'batch_size': 1, 'throughput': 0.8696832510582204, 'latency_mean': 1.149750324487686, 'latency_p50': 1.150319218635559, 'latency_p90': 1.268266987800598}, {'batch_size': 4, 'throughput': 1.8613166640558052, 'latency_mean': 2.1382693815231324, 'latency_p50': 2.1476703882217407, 'latency_p90': 2.3536849498748778}, {'batch_size': 5, 'throughput': 1.983128886216792, 'latency_mean': 2.5120989012718202, 'latency_p50': 2.5298067331314087, 'latency_p90': 2.7633197784423826}, {'batch_size': 8, 'throughput': 2.1996106792976353, 'latency_mean': 3.602684267759323, 'latency_p50': 3.5879119634628296, 'latency_p90': 4.09387400150299}, {'batch_size': 10, 'throughput': 2.214206555426689, 'latency_mean': 4.479609251022339, 'latency_p50': 4.509705543518066, 'latency_p90': 5.085396838188172}, {'batch_size': 12, 'throughput': 2.217717965525334, 'latency_mean': 5.363757123947144, 'latency_p50': 5.40757954120636, 'latency_p90': 6.091878628730774}, {'batch_size': 15, 'throughput': 2.1833794570914486, 'latency_mean': 6.785050321817398, 'latency_p50': 6.7830798625946045, 'latency_p90': 7.645038104057312}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Sao10K/Hanami-1
model_name: Hanami1
model_num_parameters: 8030261248.0
model_repo: Sao10K/Hanami-1
model_size: 8B
num_battles: 13451
num_wins: 7026
propriety_score: 0.7206512425021423
propriety_total_count: 1167.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.22
timestamp: 2024-09-06T21:52:27+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.5223403464426437
Download Preference Data
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-hanami-1-v1-mkmlizer
Waiting for job on sao10k-hanami-1-v1-mkmlizer to finish
sao10k-hanami-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-hanami-1-v1-mkmlizer: ║ _____ __ __ ║
sao10k-hanami-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-hanami-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-hanami-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-hanami-1-v1-mkmlizer: ║ /___/ ║
sao10k-hanami-1-v1-mkmlizer: ║ ║
sao10k-hanami-1-v1-mkmlizer: ║ Version: 0.10.1 ║
sao10k-hanami-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-hanami-1-v1-mkmlizer: ║ https://mk1.ai ║
sao10k-hanami-1-v1-mkmlizer: ║ ║
sao10k-hanami-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-hanami-1-v1-mkmlizer: ║ belonging to: ║
sao10k-hanami-1-v1-mkmlizer: ║ ║
sao10k-hanami-1-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-hanami-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-hanami-1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-hanami-1-v1-mkmlizer: ║ ║
sao10k-hanami-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-hanami-1-v1-mkmlizer: Downloaded to shared memory in 34.496s
sao10k-hanami-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa8m2k1r5, device:0
sao10k-hanami-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-hanami-1-v1-mkmlizer: quantized model in 26.442s
sao10k-hanami-1-v1-mkmlizer: Processed model Sao10K/Hanami-1 in 60.938s
sao10k-hanami-1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-hanami-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-hanami-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-hanami-1-v1
sao10k-hanami-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-hanami-1-v1/config.json
sao10k-hanami-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-hanami-1-v1/special_tokens_map.json
sao10k-hanami-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-hanami-1-v1/tokenizer_config.json
sao10k-hanami-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-hanami-1-v1/tokenizer.json
sao10k-hanami-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-hanami-1-v1/flywheel_model.0.safetensors
sao10k-hanami-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:34, 2.40s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:05, 1.54it/s] Loading 0: 4%|▍ | 13/291 [00:05<01:06, 4.19it/s] Loading 0: 7%|▋ | 19/291 [00:05<00:38, 7.12it/s] Loading 0: 8%|▊ | 24/291 [00:05<00:27, 9.56it/s] Loading 0: 11%|█ | 32/291 [00:05<00:16, 15.60it/s] Loading 0: 13%|█▎ | 38/291 [00:05<00:13, 19.29it/s] Loading 0: 15%|█▍ | 43/291 [00:05<00:10, 22.77it/s] Loading 0: 17%|█▋ | 50/291 [00:05<00:08, 29.45it/s] Loading 0: 19%|█▉ | 56/291 [00:05<00:07, 31.73it/s] Loading 0: 21%|██ | 61/291 [00:06<00:06, 34.33it/s] Loading 0: 24%|██▎ | 69/291 [00:06<00:05, 38.04it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:04, 46.56it/s] Loading 0: 29%|██▊ | 83/291 [00:06<00:06, 32.77it/s] Loading 0: 30%|███ | 88/291 [00:06<00:05, 34.41it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:04, 40.25it/s] Loading 0: 35%|███▍ | 101/291 [00:07<00:04, 40.42it/s] Loading 0: 36%|███▋ | 106/291 [00:07<00:04, 41.56it/s] Loading 0: 39%|███▉ | 113/291 [00:07<00:03, 46.59it/s] Loading 0: 41%|████ | 119/291 [00:07<00:03, 44.22it/s] Loading 0: 43%|████▎ | 124/291 [00:07<00:03, 43.81it/s] Loading 0: 45%|████▍ | 130/291 [00:07<00:03, 47.13it/s] Loading 0: 46%|████▋ | 135/291 [00:07<00:03, 46.82it/s] Loading 0: 48%|████▊ | 140/291 [00:07<00:03, 46.75it/s] Loading 0: 50%|████▉ | 145/291 [00:08<00:03, 46.71it/s] Loading 0: 52%|█████▏ | 150/291 [00:08<00:03, 39.32it/s] Loading 0: 54%|█████▍ | 158/291 [00:08<00:02, 48.35it/s] Loading 0: 56%|█████▋ | 164/291 [00:08<00:02, 45.76it/s] Loading 0: 58%|█████▊ | 169/291 [00:08<00:02, 45.32it/s] Loading 0: 60%|██████ | 176/291 [00:08<00:02, 50.11it/s] Loading 0: 63%|██████▎ | 182/291 [00:08<00:02, 44.06it/s] Loading 0: 64%|██████▍ | 187/291 [00:08<00:02, 44.93it/s] Loading 0: 67%|██████▋ | 194/291 [00:09<00:01, 51.14it/s] Loading 0: 69%|██████▊ | 200/291 [00:09<00:01, 48.41it/s] Loading 0: 71%|███████ | 206/291 [00:09<00:02, 33.99it/s] Loading 0: 73%|███████▎ | 211/291 [00:09<00:02, 36.95it/s] Loading 0: 74%|███████▍ | 216/291 [00:09<00:01, 38.86it/s] Loading 0: 76%|███████▋ | 222/291 [00:09<00:01, 36.58it/s] Loading 0: 79%|███████▉ | 230/291 [00:10<00:01, 44.52it/s] Loading 0: 81%|████████ | 236/291 [00:10<00:01, 42.68it/s] Loading 0: 83%|████████▎ | 241/291 [00:10<00:01, 42.48it/s] Loading 0: 85%|████████▌ | 248/291 [00:10<00:00, 47.75it/s] Loading 0: 87%|████████▋ | 254/291 [00:10<00:00, 45.45it/s] Loading 0: 89%|████████▉ | 259/291 [00:10<00:00, 43.15it/s] Loading 0: 91%|█████████ | 265/291 [00:10<00:00, 46.09it/s] Loading 0: 93%|█████████▎| 270/291 [00:10<00:00, 46.09it/s] Loading 0: 95%|█████████▍| 276/291 [00:11<00:00, 40.90it/s] Loading 0: 97%|█████████▋| 283/291 [00:11<00:00, 46.74it/s] Loading 0: 99%|█████████▉| 288/291 [00:11<00:00, 45.50it/s]
Job sao10k-hanami-1-v1-mkmlizer completed after 84.19s with status: succeeded
Stopping job with name sao10k-hanami-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-hanami-1-v1
Waiting for inference service sao10k-hanami-1-v1 to be ready
Inference service sao10k-hanami-1-v1 ready after 151.89241766929626s
Pipeline stage MKMLDeployer completed in 152.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8685634136199951s
Received healthy response to inference request in 1.53019380569458s
Received healthy response to inference request in 2.0782642364501953s
Received healthy response to inference request in 1.5667667388916016s
Received healthy response to inference request in 1.3484382629394531s
5 requests
0 failed requests
5th percentile: 1.3847893714904784
10th percentile: 1.421140480041504
20th percentile: 1.4938426971435548
30th percentile: 1.5375083923339843
40th percentile: 1.552137565612793
50th percentile: 1.5667667388916016
60th percentile: 1.687485408782959
70th percentile: 1.8082040786743163
80th percentile: 1.9105035781860351
90th percentile: 1.9943839073181153
95th percentile: 2.036324071884155
99th percentile: 2.069876203536987
mean time: 1.678445291519165
Pipeline stage StressChecker completed in 9.13s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.63s
Shutdown handler de-registered
sao10k-hanami-1_v1 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-hanami-1-v1-profiler
Waiting for inference service sao10k-hanami-1-v1-profiler to be ready
Inference service sao10k-hanami-1-v1-profiler ready after 150.382230758667s
Pipeline stage MKMLProfilerDeployer completed in 150.82s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sao10k-hanami-1-v1-profiler-predictor-00001-deployment-7b7mpcmt:/code/chaiverse_profiler_1725660004 --namespace tenant-chaiml-guanaco
kubectl exec -it sao10k-hanami-1-v1-profiler-predictor-00001-deployment-7b7mpcmt --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725660004 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1725660004/summary.json'
kubectl exec -it sao10k-hanami-1-v1-profiler-predictor-00001-deployment-7b7mpcmt --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725660004/summary.json'
Pipeline stage MKMLProfilerRunner completed in 808.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sao10k-hanami-1-v1-profiler is running
Tearing down inference service sao10k-hanami-1-v1-profiler
Service sao10k-hanami-1-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.86s
Shutdown handler de-registered
sao10k-hanami-1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics