developer_uid: junhua024
submission_id: junhua024-chai-1-full-066126_v17
model_name: junhua024-chai-1-full-066126_v17
model_group: junhua024/chai-1-full-06
status: torndown
timestamp: 2025-07-14T06:24:42+00:00
num_battles: 8117
num_wins: 3827
celo_rating: 1275.8
family_friendly_score: 0.5489999999999999
family_friendly_standard_error: 0.007037030623778754
submission_type: basic
model_repo: junhua024/chai-1-full-066126
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': 0.5875109681251098, 'latency_mean': 1.7019151043891907, 'latency_p50': 1.6979426145553589, 'latency_p90': 1.8707975149154663}, {'batch_size': 3, 'throughput': 1.0482551199355554, 'latency_mean': 2.854046105146408, 'latency_p50': 2.8513375520706177, 'latency_p90': 3.190235161781311}, {'batch_size': 5, 'throughput': 1.257653090088671, 'latency_mean': 3.9560257732868194, 'latency_p50': 3.9639774560928345, 'latency_p90': 4.393206191062927}, {'batch_size': 6, 'throughput': 1.3186832748624524, 'latency_mean': 4.527247015237808, 'latency_p50': 4.526320815086365, 'latency_p90': 5.116727876663208}, {'batch_size': 8, 'throughput': 1.3723836101410516, 'latency_mean': 5.790226927995682, 'latency_p50': 5.800103068351746, 'latency_p90': 6.539730072021484}, {'batch_size': 10, 'throughput': 1.3933643705396583, 'latency_mean': 7.117495230436325, 'latency_p50': 7.1423659324646, 'latency_p90': 7.875896716117858}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-1-full-066126_v17
is_internal_developer: False
language_model: junhua024/chai-1-full-066126
model_size: 13B
ranking_group: single
throughput_3p7s: 1.23
us_pacific_date: 2025-07-13
win_ratio: 0.471479610693606
generation_params: {'temperature': 1.0, 'top_p': 1.0, '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': '{memory}What feelings and emotions are behind these words?', '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-1-full-066126-v17-mkmlizer
Waiting for job on junhua024-chai-1-full-066126-v17-mkmlizer to finish
junhua024-chai-1-full-066126-v17-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-066126-v17-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-066126-v17-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v17-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-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-1-full-066126-v17-mkmlizer: Downloaded to shared memory in 77.177s
junhua024-chai-1-full-066126-v17-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-066126-v17-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7k05zidp, device:0
junhua024-chai-1-full-066126-v17-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-066126-v17-mkmlizer: quantized model in 32.084s
junhua024-chai-1-full-066126-v17-mkmlizer: Processed model junhua024/chai-1-full-066126 in 109.352s
junhua024-chai-1-full-066126-v17-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-066126-v17-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-066126-v17-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v17/nvidia
junhua024-chai-1-full-066126-v17-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v17/nvidia/config.json
junhua024-chai-1-full-066126-v17-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v17/nvidia/special_tokens_map.json
junhua024-chai-1-full-066126-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v17/nvidia/tokenizer_config.json
junhua024-chai-1-full-066126-v17-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v17/nvidia/tokenizer.json
junhua024-chai-1-full-066126-v17-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v17/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-1-full-066126-v17-mkmlizer completed after 136.84s with status: succeeded
Stopping job with name junhua024-chai-1-full-066126-v17-mkmlizer
Pipeline stage MKMLizer completed in 137.36s
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 junhua024-chai-1-full-066126-v17
Waiting for inference service junhua024-chai-1-full-066126-v17 to be ready
Failed to get response for submission junhua024-chai-1-full-066126_v15: ('http://junhua024-chai-1-full-066126-v15-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:33828->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission junhua024-chai-1-full-066126_v16: HTTPConnectionPool(host='junhua024-chai-1-full-066126-v16-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-1-full-066126-v17 ready after 221.28743314743042s
Pipeline stage MKMLDeployer completed in 221.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3923678398132324s
Received healthy response to inference request in 1.6221997737884521s
Received healthy response to inference request in 1.5765905380249023s
Received healthy response to inference request in 1.8597478866577148s
Received healthy response to inference request in 2.0578413009643555s
5 requests
0 failed requests
5th percentile: 1.5857123851776123
10th percentile: 1.5948342323303222
20th percentile: 1.6130779266357422
30th percentile: 1.6697093963623046
40th percentile: 1.7647286415100099
50th percentile: 1.8597478866577148
60th percentile: 1.938985252380371
70th percentile: 2.018222618103027
80th percentile: 2.124746608734131
90th percentile: 2.2585572242736816
95th percentile: 2.3254625320434568
99th percentile: 2.3789867782592773
mean time: 1.9017494678497315
Pipeline stage StressChecker completed in 10.86s
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 0.74s
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 0.76s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v17 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-1-full-066126-v17-profiler
Waiting for inference service junhua024-chai-1-full-066126-v17-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...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5410.20s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v17 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-066126_v17 status is now torndown due to DeploymentManager action