junhua024-chai-16-full-qkv_72

developer_uid: junhua024

submission_id: junhua024-chai-16-full-qkv_72_v6

model_name: junhua024-chai-16-full-qkv_72_v6

model_group: junhua024/chai_16_full_q

status: torndown

timestamp: 2025-07-20T15:31:04+00:00

num_battles: 7762

num_wins: 3765

celo_rating: 1274.58

family_friendly_score: 0.5534

family_friendly_standard_error: 0.007030625007778469

submission_type: basic

model_repo: junhua024/chai_16_full_qkv100_o106_ffn106_1624

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5850073970804336, 'latency_mean': 1.7092302680015563, 'latency_p50': 1.7078914642333984, 'latency_p90': 1.8884294748306274}, {'batch_size': 3, 'throughput': 1.0546546788964786, 'latency_mean': 2.8353893196582796, 'latency_p50': 2.8367778062820435, 'latency_p90': 3.125398540496826}, {'batch_size': 5, 'throughput': 1.2587574821634966, 'latency_mean': 3.9470617353916166, 'latency_p50': 3.9544116258621216, 'latency_p90': 4.398456788063049}, {'batch_size': 6, 'throughput': 1.3194245613175468, 'latency_mean': 4.52313462972641, 'latency_p50': 4.507323741912842, 'latency_p90': 5.060380554199218}, {'batch_size': 8, 'throughput': 1.3762920814323254, 'latency_mean': 5.766120103597641, 'latency_p50': 5.809957265853882, 'latency_p90': 6.4485169649124146}, {'batch_size': 10, 'throughput': 1.4082168128732846, 'latency_mean': 7.042181397676468, 'latency_p50': 7.058742642402649, 'latency_p90': 7.927558517456054}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-16-full-qkv_72_v6

is_internal_developer: False

language_model: junhua024/chai_16_full_qkv100_o106_ffn106_1624

model_size: 13B

ranking_group: single

throughput_3p7s: 1.23

us_pacific_date: 2025-07-20

win_ratio: 0.4850553980932749

generation_params: {'temperature': 1.0, 'top_p': 0.88, 'min_p': 0.0, 'top_k': 10, '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 junhua024-chai-16-full-qkv-72-v6-mkmlizer
Waiting for job on junhua024-chai-16-full-qkv-72-v6-mkmlizer to finish
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
Failed to get response for submission junhua024-chai-16-full-_94000_v6: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-16-full-qkv-72-v6-mkmlizer: quantized model in 31.627s
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Processed model junhua024/chai_16_full_qkv100_o106_ffn106_1624 in 120.305s
junhua024-chai-16-full-qkv-72-v6-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-qkv-72-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-qkv-72-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v6/nvidia
junhua024-chai-16-full-qkv-72-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v6/nvidia/config.json
junhua024-chai-16-full-qkv-72-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v6/nvidia/special_tokens_map.json
junhua024-chai-16-full-qkv-72-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v6/nvidia/tokenizer_config.json
junhua024-chai-16-full-qkv-72-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v6/nvidia/tokenizer.json
junhua024-chai-16-full-qkv-72-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v6/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-16-full-qkv-72-v6-mkmlizer completed after 151.47s with status: succeeded
Stopping job with name junhua024-chai-16-full-qkv-72-v6-mkmlizer
Pipeline stage MKMLizer completed in 152.05s
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 junhua024-chai-16-full-qkv-72-v6
Waiting for inference service junhua024-chai-16-full-qkv-72-v6 to be ready
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_94000_v9: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v9-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-qkv-72-v6 ready after 332.383095741272s
Pipeline stage MKMLDeployer completed in 332.86s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.4901676177978516s
Received healthy response to inference request in 2.041517734527588s
Received healthy response to inference request in 1.8730814456939697s
Received healthy response to inference request in 1.51082444190979s
5 requests
1 failed requests
5th percentile: 1.583275842666626
10th percentile: 1.655727243423462
20th percentile: 1.8006300449371337
30th percentile: 1.9067687034606933
40th percentile: 1.9741432189941406
50th percentile: 2.041517734527588
60th percentile: 2.2209776878356933
70th percentile: 2.4004376411437987
80th percentile: 6.02875170707703
90th percentile: 13.105919885635377
95th percentile: 16.64450397491455
99th percentile: 19.47537124633789
mean time: 5.619735860824585
%s, retrying in %s seconds...
Received healthy response to inference request in 1.7780494689941406s
Received healthy response to inference request in 2.3164470195770264s
Received healthy response to inference request in 1.8712575435638428s
Received healthy response to inference request in 1.8074488639831543s
Received healthy response to inference request in 1.6045093536376953s
5 requests
0 failed requests
5th percentile: 1.6392173767089844
10th percentile: 1.6739253997802734
20th percentile: 1.7433414459228516
30th percentile: 1.7839293479919434
40th percentile: 1.7956891059875488
50th percentile: 1.8074488639831543
60th percentile: 1.8329723358154297
70th percentile: 1.8584958076477052
80th percentile: 1.9602954387664795
90th percentile: 2.138371229171753
95th percentile: 2.2274091243743896
99th percentile: 2.298639440536499
mean time: 1.875542449951172
Pipeline stage StressChecker completed in 40.52s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
Failed to get response for submission junhua024-chai-16-full-_94000_v6: HTTPConnectionPool(host='junhua024-chai-16-full-94000-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.74s
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 0.89s
Shutdown handler de-registered
junhua024-chai-16-full-qkv_72_v6 status is now deployed due to DeploymentManager action
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 5515.98s
Shutdown handler de-registered
junhua024-chai-16-full-qkv_72_v6 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-qkv_72_v6 status is now torndown due to DeploymentManager action