developer_uid: cycy233
submission_id: sao10k-14b-qwen2-5-kunou-v1_v6
model_name: sao10k-14b-qwen2-5-kunou-v1_v6
model_group: Sao10K/14B-Qwen2.5-Kunou
status: torndown
timestamp: 2025-05-07T03:54:22+00:00
num_battles: 6583
num_wins: 2944
celo_rating: 1241.89
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: Sao10K/14B-Qwen2.5-Kunou-v1
model_architecture: Qwen2ForCausalLM
model_num_parameters: 14769689600.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.47354401084152026, 'latency_mean': 2.11164417386055, 'latency_p50': 2.1207982301712036, 'latency_p90': 2.3421826362609863}, {'batch_size': 3, 'throughput': 0.8742951974885325, 'latency_mean': 3.41712802529335, 'latency_p50': 3.439294695854187, 'latency_p90': 3.744102954864502}, {'batch_size': 5, 'throughput': 1.0538557501248214, 'latency_mean': 4.7147600877285, 'latency_p50': 4.698009252548218, 'latency_p90': 5.2655411720275875}, {'batch_size': 6, 'throughput': 1.1047679707243905, 'latency_mean': 5.399363714456558, 'latency_p50': 5.3995361328125, 'latency_p90': 6.009394812583923}, {'batch_size': 10, 'throughput': 1.1916760009156488, 'latency_mean': 8.335318526029587, 'latency_p50': 8.361835956573486, 'latency_p90': 9.299549531936645}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sao10k-14b-qwen2-5-kunou-v1_v6
is_internal_developer: False
language_model: Sao10K/14B-Qwen2.5-Kunou-v1
model_size: 15B
ranking_group: single
throughput_3p7s: 0.93
us_pacific_date: 2025-05-06
win_ratio: 0.4472125170894729
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.1, '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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-14b-qwen2-5-kunou-v1-v6-mkmlizer
Waiting for job on sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer to finish
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ _____ __ __ ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ /___/ ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ Version: 0.12.8 ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ https://mk1.ai ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ belonging to: ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ Chai Research Corp. ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: Downloaded to shared memory in 44.390s
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpf4bn8_v0, device:0
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: quantized model in 35.734s
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: Processed model Sao10K/14B-Qwen2.5-Kunou-v1 in 80.126s
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: creating bucket guanaco-mkml-models
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v6
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v6/config.json
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v6/added_tokens.json
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v6/tokenizer_config.json
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v6/special_tokens_map.json
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v6/merges.txt
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v6/vocab.json
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v6/tokenizer.json
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v6/flywheel_model.1.safetensors
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v6/flywheel_model.0.safetensors
sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 0%| | 2/579 [00:06<33:21, 3.47s/it] Loading 0: 3%|▎ | 16/579 [00:07<03:01, 3.10it/s] Loading 0: 5%|▌ | 30/579 [00:07<01:19, 6.90it/s] Loading 0: 9%|▉ | 52/579 [00:07<00:35, 14.95it/s] Loading 0: 11%|█▏ | 66/579 [00:07<00:24, 21.19it/s] Loading 0: 15%|█▌ | 88/579 [00:07<00:14, 34.25it/s] Loading 0: 18%|█▊ | 103/579 [00:07<00:10, 43.57it/s] Loading 0: 21%|██▏ | 124/579 [00:07<00:07, 60.65it/s] Loading 0: 24%|██▍ | 140/579 [00:07<00:06, 71.69it/s] Loading 0: 27%|██▋ | 155/579 [00:08<00:07, 56.89it/s] Loading 0: 30%|██▉ | 172/579 [00:08<00:05, 70.67it/s] Loading 0: 32%|███▏ | 186/579 [00:08<00:04, 79.10it/s] Loading 0: 36%|███▌ | 208/579 [00:08<00:03, 101.18it/s] Loading 0: 39%|███▊ | 223/579 [00:08<00:03, 106.78it/s] Loading 0: 42%|████▏ | 244/579 [00:08<00:02, 124.45it/s] Loading 0: 45%|████▍ | 260/579 [00:08<00:02, 126.99it/s] Loading 0: 48%|████▊ | 280/579 [00:09<00:02, 138.14it/s] Loading 0: 51%|█████ | 296/579 [00:09<00:02, 136.73it/s] Loading 0: 55%|█████▍ | 316/579 [00:09<00:01, 146.22it/s] Loading 0: 57%|█████▋ | 332/579 [00:09<00:01, 142.89it/s] Loading 0: 61%|██████ | 352/579 [00:09<00:01, 151.65it/s] Loading 0: 64%|██████▎ | 368/579 [00:09<00:02, 87.02it/s] Loading 0: 67%|██████▋ | 388/579 [00:10<00:01, 103.27it/s] Loading 0: 69%|██████▉ | 402/579 [00:10<00:01, 106.28it/s] Loading 0: 73%|███████▎ | 424/579 [00:10<00:01, 125.67it/s] Loading 0: 76%|███████▌ | 439/579 [00:10<00:01, 126.05it/s] Loading 0: 79%|███████▉ | 460/579 [00:10<00:00, 140.59it/s] Loading 0: 82%|████████▏ | 476/579 [00:10<00:00, 138.76it/s] Loading 0: 85%|████████▍ | 491/579 [00:25<00:23, 3.76it/s] Loading 0: 88%|████████▊ | 508/579 [00:25<00:13, 5.32it/s] Loading 0: 91%|█████████ | 524/579 [00:25<00:07, 7.36it/s] Loading 0: 94%|█████████▍| 544/579 [00:25<00:03, 10.90it/s] Loading 0: 97%|█████████▋| 560/579 [00:25<00:01, 14.67it/s] Loading 0: 100%|█████████▉| 578/579 [00:25<00:00, 20.51it/s]
Job sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer completed after 104.72s with status: succeeded
Stopping job with name sao10k-14b-qwen2-5-kunou-v1-v6-mkmlizer
Pipeline stage MKMLizer completed in 105.25s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-14b-qwen2-5-kunou-v1-v6
Waiting for inference service sao10k-14b-qwen2-5-kunou-v1-v6 to be ready
Inference service sao10k-14b-qwen2-5-kunou-v1-v6 ready after 220.88249826431274s
Pipeline stage MKMLDeployer completed in 221.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7826390266418457s
Received healthy response to inference request in 1.8707740306854248s
Received healthy response to inference request in 1.8912925720214844s
Received healthy response to inference request in 1.8107895851135254s
Received healthy response to inference request in 1.6602215766906738s
5 requests
0 failed requests
5th percentile: 1.690335178375244
10th percentile: 1.7204487800598145
20th percentile: 1.7806759834289552
30th percentile: 1.8227864742279052
40th percentile: 1.846780252456665
50th percentile: 1.8707740306854248
60th percentile: 1.8789814472198487
70th percentile: 1.8871888637542724
80th percentile: 2.069561862945557
90th percentile: 2.4261004447937013
95th percentile: 2.604369735717773
99th percentile: 2.746985168457031
mean time: 2.0031433582305906
Pipeline stage StressChecker completed in 11.44s
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 0.95s
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 0.86s
Shutdown handler de-registered
sao10k-14b-qwen2-5-kunou-v1_v6 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 0.11s
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 sao10k-14b-qwen2-5-kunou-v1-v6-profiler
Waiting for inference service sao10k-14b-qwen2-5-kunou-v1-v6-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
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Received signal 15, running shutdown handler
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 2493.53s
Shutdown handler de-registered
sao10k-14b-qwen2-5-kunou-v1_v6 status is now torndown due to DeploymentManager action