junhua024-chai-06-full-_72764

developer_uid: junhua024

submission_id: junhua024-chai-06-full-_72764_v2

model_name: junhua024-chai-06-full-_72764_v2

model_group: junhua024/chai_06_full_0

status: torndown

timestamp: 2025-07-17T11:31:14+00:00

num_battles: 5846

num_wins: 2992

celo_rating: 1291.45

family_friendly_score: 0.5554

family_friendly_standard_error: 0.007027529295563271

submission_type: basic

model_repo: junhua024/chai_06_full_02102_2024

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': 0.5904189215115587, 'latency_mean': 1.6935453164577483, 'latency_p50': 1.6970194578170776, 'latency_p90': 1.869901418685913}, {'batch_size': 3, 'throughput': 1.0835785031880953, 'latency_mean': 2.7569675159454348, 'latency_p50': 2.7598956823349, 'latency_p90': 3.068850874900818}, {'batch_size': 5, 'throughput': 1.296513225391356, 'latency_mean': 3.8375983107089997, 'latency_p50': 3.8476229906082153, 'latency_p90': 4.302156233787537}, {'batch_size': 6, 'throughput': 1.3579057172477027, 'latency_mean': 4.389753450155258, 'latency_p50': 4.404446959495544, 'latency_p90': 4.899209642410279}, {'batch_size': 8, 'throughput': 1.4238850147018542, 'latency_mean': 5.582995692491531, 'latency_p50': 5.607234835624695, 'latency_p90': 6.187947845458984}, {'batch_size': 10, 'throughput': 1.460997415745942, 'latency_mean': 6.788200978040695, 'latency_p50': 6.680992484092712, 'latency_p90': 7.775040531158448}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-06-full-_72764_v2

is_internal_developer: False

language_model: junhua024/chai_06_full_02102_2024

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-07-17

win_ratio: 0.5118029421826891

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-06-full-72764-v2-mkmlizer
Waiting for job on junhua024-chai-06-full-72764-v2-mkmlizer to finish
junhua024-chai-06-full-72764-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-72764-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-72764-v2-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-72764-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-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-06-full-72764-v2-mkmlizer: Downloaded to shared memory in 128.683s
junhua024-chai-06-full-72764-v2-mkmlizer: Checking if junhua024/chai_06_full_02102_2024 already exists in ChaiML
junhua024-chai-06-full-72764-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1p4x9xb_, device:0
junhua024-chai-06-full-72764-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-72764-v2-mkmlizer: quantized model in 31.051s
junhua024-chai-06-full-72764-v2-mkmlizer: Processed model junhua024/chai_06_full_02102_2024 in 159.810s
junhua024-chai-06-full-72764-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-72764-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-72764-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-72764-v2/nvidia
junhua024-chai-06-full-72764-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-72764-v2/nvidia/config.json
junhua024-chai-06-full-72764-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-72764-v2/nvidia/special_tokens_map.json
junhua024-chai-06-full-72764-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-72764-v2/nvidia/tokenizer_config.json
junhua024-chai-06-full-72764-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-72764-v2/nvidia/tokenizer.json
junhua024-chai-06-full-72764-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-72764-v2/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-06-full-72764-v2-mkmlizer completed after 201.55s with status: succeeded
Stopping job with name junhua024-chai-06-full-72764-v2-mkmlizer
Pipeline stage MKMLizer completed in 202.12s
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-06-full-72764-v2
Waiting for inference service junhua024-chai-06-full-72764-v2 to be ready
Inference service junhua024-chai-06-full-72764-v2 ready after 302.2656190395355s
Pipeline stage MKMLDeployer completed in 302.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.241008758544922s
Received healthy response to inference request in 1.5982084274291992s
Received healthy response to inference request in 2.0166380405426025s
Received healthy response to inference request in 1.5413384437561035s
Received healthy response to inference request in 1.607928991317749s
5 requests
0 failed requests
5th percentile: 1.5527124404907227
10th percentile: 1.5640864372253418
20th percentile: 1.58683443069458
30th percentile: 1.6001525402069092
40th percentile: 1.604040765762329
50th percentile: 1.607928991317749
60th percentile: 1.7714126110076904
70th percentile: 1.9348962306976318
80th percentile: 2.0615121841430666
90th percentile: 2.1512604713439942
95th percentile: 2.196134614944458
99th percentile: 2.232033929824829
mean time: 1.8010245323181153
Pipeline stage StressChecker completed in 10.32s
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 0.73s
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 0.75s
Shutdown handler de-registered
junhua024-chai-06-full-_72764_v2 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 3216.51s
Shutdown handler de-registered
junhua024-chai-06-full-_72764_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-_72764_v2 status is now torndown due to DeploymentManager action
junhua024-chai-06-full-_72764_v2 status is now torndown due to DeploymentManager action