developer_uid: huohuo12
submission_id: sao10k-14b-qwen2-5-kunou-v1_v4
model_name: sao10k-14b-qwen2-5-kunou-v1_v3
model_group: Sao10K/14B-Qwen2.5-Kunou
status: torndown
timestamp: 2025-02-19T03:25:26+00:00
num_battles: 5518
num_wins: 2623
celo_rating: 1242.15
family_friendly_score: 0.6122000000000001
family_friendly_standard_error: 0.006890735229277062
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
latencies: [{'batch_size': 1, 'throughput': 0.4734139656412165, 'latency_mean': 2.112250669002533, 'latency_p50': 2.1248120069503784, 'latency_p90': 2.324985909461975}, {'batch_size': 3, 'throughput': 0.8653880504906394, 'latency_mean': 3.4556761705875396, 'latency_p50': 3.4528898000717163, 'latency_p90': 3.761413073539734}, {'batch_size': 5, 'throughput': 1.0430270284120908, 'latency_mean': 4.772726879119873, 'latency_p50': 4.731736540794373, 'latency_p90': 5.317944931983948}, {'batch_size': 6, 'throughput': 1.0977731008285991, 'latency_mean': 5.4354048144817355, 'latency_p50': 5.406180381774902, 'latency_p90': 6.115119886398316}, {'batch_size': 10, 'throughput': 1.1913358255395312, 'latency_mean': 8.329269448518753, 'latency_p50': 8.324717044830322, 'latency_p90': 9.380514001846313}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: sao10k-14b-qwen2-5-kunou-v1_v3
is_internal_developer: False
language_model: Sao10K/14B-Qwen2.5-Kunou-v1
model_size: 15B
ranking_group: single
throughput_3p7s: 0.91
us_pacific_date: 2025-02-18
win_ratio: 0.475353388909025
generation_params: {'temperature': 1.05, 'top_p': 0.95, 'min_p': 0.03, 'top_k': 55, 'presence_penalty': 0.65, 'frequency_penalty': 0.3, '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-14b-qwen2-5-kunou-v1-v4-mkmlizer
Waiting for job on sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer to finish
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ _____ __ __ ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ /___/ ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ Version: 0.12.8 ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ https://mk1.ai ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ belonging to: ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ Chai Research Corp. ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ║ ║
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: Downloaded to shared memory in 31.591s
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwvi7gv0b, device:0
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: quantized model in 37.159s
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: Processed model Sao10K/14B-Qwen2.5-Kunou-v1 in 68.751s
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: creating bucket guanaco-mkml-models
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v4
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v4/config.json
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v4/added_tokens.json
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v4/special_tokens_map.json
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v4/tokenizer_config.json
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v4/merges.txt
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v4/vocab.json
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v4/tokenizer.json
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-14b-qwen2-5-kunou-v1-v4/flywheel_model.0.safetensors
sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer: Loading 0: 0%| | 0/579 [00:00<?, ?it/s] Loading 0: 0%| | 2/579 [00:07<34:11, 3.56s/it] Loading 0: 3%|▎ | 16/579 [00:07<03:06, 3.02it/s] Loading 0: 5%|▌ | 29/579 [00:07<01:25, 6.47it/s] Loading 0: 7%|▋ | 42/579 [00:07<00:48, 11.05it/s] Loading 0: 10%|█ | 60/579 [00:07<00:26, 19.52it/s] Loading 0: 13%|█▎ | 76/579 [00:07<00:17, 28.73it/s] Loading 0: 16%|█▌ | 90/579 [00:07<00:13, 37.38it/s] Loading 0: 19%|█▊ | 108/579 [00:07<00:08, 52.43it/s] Loading 0: 21%|██▏ | 124/579 [00:08<00:06, 65.55it/s] Loading 0: 24%|██▍ | 138/579 [00:08<00:05, 73.52it/s] Loading 0: 26%|██▌ | 151/579 [00:08<00:08, 51.50it/s] Loading 0: 29%|██▉ | 168/579 [00:08<00:06, 67.00it/s] Loading 0: 32%|███▏ | 184/579 [00:08<00:04, 80.58it/s] Loading 0: 34%|███▍ | 197/579 [00:08<00:04, 88.85it/s] Loading 0: 36%|███▋ | 210/579 [00:09<00:03, 95.94it/s] Loading 0: 39%|███▉ | 228/579 [00:09<00:03, 113.62it/s] Loading 0: 42%|████▏ | 244/579 [00:09<00:02, 122.12it/s] Loading 0: 45%|████▍ | 259/579 [00:09<00:02, 120.20it/s] Loading 0: 48%|████▊ | 276/579 [00:09<00:02, 130.59it/s] Loading 0: 50%|█████ | 292/579 [00:09<00:02, 133.76it/s] Loading 0: 53%|█████▎ | 307/579 [00:09<00:02, 125.93it/s] Loading 0: 56%|█████▌ | 324/579 [00:09<00:01, 136.07it/s] Loading 0: 59%|█████▊ | 340/579 [00:09<00:01, 138.74it/s] Loading 0: 61%|██████▏ | 355/579 [00:10<00:01, 131.27it/s] Loading 0: 64%|██████▎ | 369/579 [00:10<00:02, 74.09it/s] Loading 0: 66%|██████▋ | 384/579 [00:10<00:02, 86.18it/s] Loading 0: 69%|██████▉ | 400/579 [00:10<00:01, 99.29it/s] Loading 0: 72%|███████▏ | 414/579 [00:10<00:01, 103.29it/s] Loading 0: 75%|███████▌ | 436/579 [00:10<00:01, 124.85it/s] Loading 0: 78%|███████▊ | 451/579 [00:11<00:01, 121.53it/s] Loading 0: 81%|████████ | 468/579 [00:11<00:00, 132.58it/s] Loading 0: 84%|████████▎ | 484/579 [00:11<00:00, 137.33it/s] Loading 0: 86%|████████▌ | 499/579 [00:26<00:23, 3.47it/s] Loading 0: 89%|████████▉ | 516/579 [00:26<00:12, 5.00it/s] Loading 0: 92%|█████████▏| 532/579 [00:26<00:06, 7.01it/s] Loading 0: 94%|█████████▍| 547/579 [00:26<00:03, 9.56it/s] Loading 0: 97%|█████████▋| 564/579 [00:26<00:01, 13.58it/s]
Job sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer completed after 93.97s with status: succeeded
Stopping job with name sao10k-14b-qwen2-5-kunou-v1-v4-mkmlizer
Pipeline stage MKMLizer completed in 94.43s
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-14b-qwen2-5-kunou-v1-v4
Waiting for inference service sao10k-14b-qwen2-5-kunou-v1-v4 to be ready
Failed to get response for submission chaiml-20250218-c-4epoc_55567_v2: HTTPConnectionPool(host='chaiml-20250218-c-4epoc-55567-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-20250218-c-4epoc_55567_v1: HTTPConnectionPool(host='chaiml-20250218-c-4epoc-55567-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service sao10k-14b-qwen2-5-kunou-v1-v4 ready after 230.7780225276947s
Pipeline stage MKMLDeployer completed in 231.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.504795789718628s
Received healthy response to inference request in 1.331120491027832s
Received healthy response to inference request in 1.2318947315216064s
Received healthy response to inference request in 1.5480139255523682s
Received healthy response to inference request in 1.416015386581421s
5 requests
0 failed requests
5th percentile: 1.2517398834228515
10th percentile: 1.2715850353240967
20th percentile: 1.311275339126587
30th percentile: 1.3480994701385498
40th percentile: 1.3820574283599854
50th percentile: 1.416015386581421
60th percentile: 1.4688148021697998
70th percentile: 1.5216142177581786
80th percentile: 1.7393702983856203
90th percentile: 2.122083044052124
95th percentile: 2.313439416885376
99th percentile: 2.4665245151519777
mean time: 1.606368064880371
Pipeline stage StressChecker completed in 9.33s
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 0.64s
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 0.64s
Shutdown handler de-registered
sao10k-14b-qwen2-5-kunou-v1_v4 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-14b-qwen2-5-kunou-v1-v4-profiler
Waiting for inference service sao10k-14b-qwen2-5-kunou-v1-v4-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 2790.99s
Shutdown handler de-registered
sao10k-14b-qwen2-5-kunou-v1_v4 status is now inactive due to auto deactivation removed underperforming models
sao10k-14b-qwen2-5-kunou-v1_v4 status is now torndown due to DeploymentManager action
sao10k-14b-qwen2-5-kunou-v1_v4 status is now torndown due to DeploymentManager action
sao10k-14b-qwen2-5-kunou-v1_v4 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1