junhua024-chai-02-full-02-019

developer_uid: junhua024

submission_id: junhua024-chai-02-full-02-019_v3

model_name: junhua024-chai-02-full-02-019_v3

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-23T20:10:11+00:00

num_battles: 6133

num_wins: 3170

celo_rating: 1294.04

family_friendly_score: 0.4144

family_friendly_standard_error: 0.006966672663474293

submission_type: basic

model_repo: junhua024/chai_02_full_02_019

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': 0.6593809617704275, 'latency_mean': 1.516376485824585, 'latency_p50': 1.505003571510315, 'latency_p90': 1.6881550073623657}, {'batch_size': 3, 'throughput': 1.11937264100524, 'latency_mean': 2.669482729434967, 'latency_p50': 2.6495898962020874, 'latency_p90': 2.9288926124572754}, {'batch_size': 5, 'throughput': 1.2903989962161824, 'latency_mean': 3.857339844703674, 'latency_p50': 3.8447059392929077, 'latency_p90': 4.340015387535095}, {'batch_size': 6, 'throughput': 1.341974216755838, 'latency_mean': 4.440451273918152, 'latency_p50': 4.4203397035598755, 'latency_p90': 5.047334337234497}, {'batch_size': 8, 'throughput': 1.39091839198281, 'latency_mean': 5.709360835552215, 'latency_p50': 5.680552124977112, 'latency_p90': 6.481982636451721}, {'batch_size': 10, 'throughput': 1.4245798373171659, 'latency_mean': 6.971316320896149, 'latency_p50': 7.001826047897339, 'latency_p90': 7.816195392608643}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full-02-019_v3

is_internal_developer: False

language_model: junhua024/chai_02_full_02_019

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-07-23

win_ratio: 0.5168759171694114

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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': "{memory} You are an empathetic conversational AI. You understand the user's feelings and respond with warmth, compassion, and sincerity.", '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-02-full-02-019-v3-mkmlizer
Waiting for job on junhua024-chai-02-full-02-019-v3-mkmlizer to finish
junhua024-chai-02-full-02-019-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-02-019-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-019-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-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-02-full-02-019-v3-mkmlizer: Downloaded to shared memory in 80.079s
junhua024-chai-02-full-02-019-v3-mkmlizer: Checking if junhua024/chai_02_full_02_019 already exists in ChaiML
junhua024-chai-02-full-02-019-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp76npe4p7, device:0
junhua024-chai-02-full-02-019-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
junhua024-chai-02-full-02-019-v3-mkmlizer: quantized model in 164.999s
junhua024-chai-02-full-02-019-v3-mkmlizer: Processed model junhua024/chai_02_full_02_019 in 245.446s
junhua024-chai-02-full-02-019-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-02-019-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-02-019-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v3/nvidia
junhua024-chai-02-full-02-019-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v3/nvidia/config.json
junhua024-chai-02-full-02-019-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v3/nvidia/special_tokens_map.json
junhua024-chai-02-full-02-019-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v3/nvidia/tokenizer_config.json
junhua024-chai-02-full-02-019-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v3/nvidia/tokenizer.json
Job junhua024-chai-02-full-02-019-v3-mkmlizer completed after 274.01s with status: succeeded
Stopping job with name junhua024-chai-02-full-02-019-v3-mkmlizer
Pipeline stage MKMLizer completed in 274.62s
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-02-full-02-019-v3
Waiting for inference service junhua024-chai-02-full-02-019-v3 to be ready
Failed to get response for submission junhua024-chai-02-full-02-019_v2: HTTPConnectionPool(host='junhua024-chai-02-full-02-019-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-02-full-02-019-v3 ready after 170.59511923789978s
Pipeline stage MKMLDeployer completed in 171.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 6.5062620639801025s
Received healthy response to inference request in 1.4553053379058838s
Received healthy response to inference request in 2.089050769805908s
Received healthy response to inference request in 2.0330145359039307s
Received healthy response to inference request in 2.420628786087036s
5 requests
0 failed requests
5th percentile: 1.570847177505493
10th percentile: 1.6863890171051026
20th percentile: 1.9174726963043214
30th percentile: 2.044221782684326
40th percentile: 2.0666362762451174
50th percentile: 2.089050769805908
60th percentile: 2.2216819763183593
70th percentile: 2.3543131828308104
80th percentile: 3.23775544166565
90th percentile: 4.872008752822876
95th percentile: 5.689135408401489
99th percentile: 6.34283673286438
mean time: 2.9008522987365724
Pipeline stage StressChecker completed in 16.20s
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 0.72s
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 0.82s
Shutdown handler de-registered
junhua024-chai-02-full-02-019_v3 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-02-full-02-019-v3-profiler
Waiting for inference service junhua024-chai-02-full-02-019-v3-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 3068.96s
Shutdown handler de-registered
junhua024-chai-02-full-02-019_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-02-019_v3 status is now torndown due to DeploymentManager action