junhua024-chai-02-full-06105

developer_uid: junhua024

submission_id: junhua024-chai-02-full-06105_v3

model_name: junhua024-chai-02-full-06105_v3

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-16T16:34:58+00:00

num_battles: 6983

num_wins: 3508

celo_rating: 1280.28

family_friendly_score: 0.5484

family_friendly_standard_error: 0.007037861038696345

submission_type: basic

model_repo: junhua024/chai_02_full_06105

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': 0.5943385333257599, 'latency_mean': 1.682371724843979, 'latency_p50': 1.6829204559326172, 'latency_p90': 1.8588128089904785}, {'batch_size': 3, 'throughput': 1.080369947908203, 'latency_mean': 2.7670561444759367, 'latency_p50': 2.7779948711395264, 'latency_p90': 3.026803398132324}, {'batch_size': 5, 'throughput': 1.2943910526003586, 'latency_mean': 3.848699514865875, 'latency_p50': 3.848830819129944, 'latency_p90': 4.3457008600234985}, {'batch_size': 6, 'throughput': 1.3471989544027037, 'latency_mean': 4.4364728832244875, 'latency_p50': 4.4454710483551025, 'latency_p90': 4.916218709945679}, {'batch_size': 8, 'throughput': 1.4098886438956337, 'latency_mean': 5.632807298898697, 'latency_p50': 5.615327954292297, 'latency_p90': 6.309019684791565}, {'batch_size': 10, 'throughput': 1.4350315743254056, 'latency_mean': 6.909434102773666, 'latency_p50': 6.935163497924805, 'latency_p90': 7.822855758666992}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full-06105_v3

is_internal_developer: False

language_model: junhua024/chai_02_full_06105

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-07-16

win_ratio: 0.5023628812831161

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-02-full-06105-v3-mkmlizer
Waiting for job on junhua024-chai-02-full-06105-v3-mkmlizer to finish
junhua024-chai-02-full-06105-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-06105-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-06105-v3-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-06105-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-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-06105-v3-mkmlizer: Downloaded to shared memory in 80.859s
junhua024-chai-02-full-06105-v3-mkmlizer: Checking if junhua024/chai_02_full_06105 already exists in ChaiML
junhua024-chai-02-full-06105-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyfb_69bd, device:0
junhua024-chai-02-full-06105-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-06105-v3-mkmlizer: quantized model in 31.393s
junhua024-chai-02-full-06105-v3-mkmlizer: Processed model junhua024/chai_02_full_06105 in 112.359s
junhua024-chai-02-full-06105-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-06105-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-06105-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-06105-v3/nvidia
junhua024-chai-02-full-06105-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-06105-v3/nvidia/config.json
junhua024-chai-02-full-06105-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-06105-v3/nvidia/special_tokens_map.json
junhua024-chai-02-full-06105-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-06105-v3/nvidia/tokenizer_config.json
junhua024-chai-02-full-06105-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-06105-v3/nvidia/tokenizer.json
junhua024-chai-02-full-06105-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-06105-v3/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-02-full-06105-v3-mkmlizer completed after 138.84s with status: succeeded
Stopping job with name junhua024-chai-02-full-06105-v3-mkmlizer
Pipeline stage MKMLizer completed in 139.36s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-06105-v3
Waiting for inference service junhua024-chai-02-full-06105-v3 to be ready
Inference service junhua024-chai-02-full-06105-v3 ready after 261.8625361919403s
Pipeline stage MKMLDeployer completed in 262.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7970147132873535s
Received healthy response to inference request in 1.775963544845581s
Received healthy response to inference request in 1.791092872619629s
Received healthy response to inference request in 2.014305591583252s
Received healthy response to inference request in 1.9610702991485596s
5 requests
0 failed requests
5th percentile: 1.7789894104003907
10th percentile: 1.7820152759552002
20th percentile: 1.7880670070648192
30th percentile: 1.8250883579254151
40th percentile: 1.8930793285369873
50th percentile: 1.9610702991485596
60th percentile: 1.9823644161224365
70th percentile: 2.0036585330963135
80th percentile: 2.1708474159240723
90th percentile: 2.483931064605713
95th percentile: 2.640472888946533
99th percentile: 2.7657063484191893
mean time: 2.067889404296875
Pipeline stage StressChecker completed in 11.69s
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 0.69s
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 1.30s
Shutdown handler de-registered
junhua024-chai-02-full-06105_v3 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 6527.27s
Shutdown handler de-registered
junhua024-chai-02-full-06105_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-06105_v3 status is now torndown due to DeploymentManager action
junhua024-chai-02-full-06105_v3 status is now torndown due to DeploymentManager action