junhua024-chai-1-full-066126

developer_uid: junhua024

submission_id: junhua024-chai-1-full-066126_v53

model_name: junhua024-chai-1-full-066126_v53

model_group: junhua024/chai-1-full-06

status: torndown

timestamp: 2025-07-15T08:09:56+00:00

num_battles: 7063

num_wins: 3624

celo_rating: 1282.82

family_friendly_score: 0.5464

family_friendly_standard_error: 0.007040554523615309

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': 0.5982053477304982, 'latency_mean': 1.6715074813365935, 'latency_p50': 1.6675379276275635, 'latency_p90': 1.8301535606384278}, {'batch_size': 3, 'throughput': 1.0842130964925252, 'latency_mean': 2.7572149538993838, 'latency_p50': 2.7725791931152344, 'latency_p90': 3.047895908355713}, {'batch_size': 5, 'throughput': 1.2941666620332235, 'latency_mean': 3.845550299882889, 'latency_p50': 3.843787431716919, 'latency_p90': 4.337973594665527}, {'batch_size': 6, 'throughput': 1.3640083382088735, 'latency_mean': 4.37958566069603, 'latency_p50': 4.364644169807434, 'latency_p90': 4.945755410194397}, {'batch_size': 8, 'throughput': 1.443277370329323, 'latency_mean': 5.499817839860916, 'latency_p50': 5.4720892906188965, 'latency_p90': 6.268083477020263}, {'batch_size': 10, 'throughput': 1.464249034845217, 'latency_mean': 6.77902162194252, 'latency_p50': 6.7368223667144775, 'latency_p90': 7.729055261611938}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-066126_v53

is_internal_developer: False

language_model: junhua024/chai-1-full-066126

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-07-15

win_ratio: 0.5130964179527113

generation_params: {'temperature': 1.0, 'top_p': 0.88, 'min_p': 0.0, 'top_k': 8, '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-1-full-066126-v53-mkmlizer
Waiting for job on junhua024-chai-1-full-066126-v53-mkmlizer to finish
junhua024-chai-1-full-066126-v53-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-066126-v53-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-066126-v53-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v53-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-066126-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-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-v53-mkmlizer: Downloaded to shared memory in 77.874s
junhua024-chai-1-full-066126-v53-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-066126-v53-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzuldz7l3, device:0
junhua024-chai-1-full-066126-v53-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-066126-v53-mkmlizer: quantized model in 31.911s
junhua024-chai-1-full-066126-v53-mkmlizer: Processed model junhua024/chai-1-full-066126 in 109.861s
junhua024-chai-1-full-066126-v53-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-066126-v53-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-066126-v53-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v53/nvidia
junhua024-chai-1-full-066126-v53-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v53/nvidia/config.json
junhua024-chai-1-full-066126-v53-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v53/nvidia/special_tokens_map.json
junhua024-chai-1-full-066126-v53-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v53/nvidia/tokenizer_config.json
junhua024-chai-1-full-066126-v53-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v53/nvidia/tokenizer.json
junhua024-chai-1-full-066126-v53-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v53/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-1-full-066126-v53-mkmlizer completed after 138.83s with status: succeeded
Stopping job with name junhua024-chai-1-full-066126-v53-mkmlizer
Pipeline stage MKMLizer completed in 139.33s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-066126-v53
Waiting for inference service junhua024-chai-1-full-066126-v53 to be ready
Unable to record family friendly update due to error: HTTPConnectionPool(host='chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x746d04556910>, 'Connection to chaiml-nemo-guard-merged-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Inference service junhua024-chai-1-full-066126-v53 ready after 441.94671988487244s
Pipeline stage MKMLDeployer completed in 442.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.103734016418457s
Received healthy response to inference request in 1.8836381435394287s
Received healthy response to inference request in 1.8040738105773926s
Received healthy response to inference request in 1.6392149925231934s
Received healthy response to inference request in 1.8291106224060059s
5 requests
0 failed requests
5th percentile: 1.6721867561340331
10th percentile: 1.705158519744873
20th percentile: 1.7711020469665528
30th percentile: 1.8090811729431153
40th percentile: 1.8190958976745606
50th percentile: 1.8291106224060059
60th percentile: 1.850921630859375
70th percentile: 1.8727326393127441
80th percentile: 2.1276573181152347
90th percentile: 2.615695667266846
95th percentile: 2.859714841842651
99th percentile: 3.0549301815032956
mean time: 2.0519543170928953
Pipeline stage StressChecker completed in 11.64s
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 1.07s
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 1.07s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v53 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3180.94s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v53 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-066126_v53 status is now torndown due to DeploymentManager action
junhua024-chai-1-full-066126_v53 status is now torndown due to DeploymentManager action