junhua024-chai-02-full-02-019

developer_uid: junhua024

submission_id: junhua024-chai-02-full-02-019_v9

model_name: junhua024-chai-02-full-02-019_v9

model_group: junhua024/chai_02_full_0

status: torndown

timestamp: 2025-07-24T05:45:21+00:00

num_battles: 6706

num_wins: 3443

celo_rating: 1292.9

family_friendly_score: 0.4124

family_friendly_standard_error: 0.006961698643291018

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: 4048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3639896238314623, 'latency_mean': 2.7471862637996676, 'latency_p50': 2.756593108177185, 'latency_p90': 2.9383859872817992}, {'batch_size': 2, 'throughput': 0.4453444715178709, 'latency_mean': 4.490671918392182, 'latency_p50': 4.506698131561279, 'latency_p90': 4.77323362827301}, {'batch_size': 3, 'throughput': 0.4807536294180851, 'latency_mean': 6.222475864887238, 'latency_p50': 6.186153292655945, 'latency_p90': 6.90266649723053}, {'batch_size': 5, 'throughput': 0.5091167303208138, 'latency_mean': 9.791744215488434, 'latency_p50': 9.838839650154114, 'latency_p90': 10.97372546195984}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-02-full-02-019_v9

is_internal_developer: False

language_model: junhua024/chai_02_full_02_019

model_size: 13B

ranking_group: single

throughput_3p7s: 0.42

us_pacific_date: 2025-07-23

win_ratio: 0.513420817178646

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': 4048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{memory} You are an empathetic conversational AI that understands the user's feelings and responds with uplifting 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-v9-mkmlizer
Waiting for job on junhua024-chai-02-full-02-019-v9-mkmlizer to finish
junhua024-chai-02-full-02-019-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-02-019-v9-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ║                                                                     ║
junhua024-chai-02-full-02-019-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-02-019-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-mkmlizer: Downloaded to shared memory in 74.400s
junhua024-chai-02-full-02-019-v9-mkmlizer: Checking if junhua024/chai_02_full_02_019 already exists in ChaiML
junhua024-chai-02-full-02-019-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpa7f1rh34, device:0
junhua024-chai-02-full-02-019-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-next-door-annoyi_15417_v1: ('http://chaiml-next-door-annoyi-15417-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
junhua024-chai-02-full-02-019-v9-mkmlizer: quantized model in 164.309s
junhua024-chai-02-full-02-019-v9-mkmlizer: Processed model junhua024/chai_02_full_02_019 in 238.791s
junhua024-chai-02-full-02-019-v9-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-02-019-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-02-019-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v9/nvidia
junhua024-chai-02-full-02-019-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v9/nvidia/special_tokens_map.json
junhua024-chai-02-full-02-019-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v9/nvidia/config.json
junhua024-chai-02-full-02-019-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v9/nvidia/tokenizer_config.json
junhua024-chai-02-full-02-019-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v9/nvidia/tokenizer.json
junhua024-chai-02-full-02-019-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-02-019-v9/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-02-full-02-019-v9-mkmlizer completed after 266.59s with status: succeeded
Stopping job with name junhua024-chai-02-full-02-019-v9-mkmlizer
Pipeline stage MKMLizer completed in 267.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Failed to get response for submission chaiml-next-door-annoyi_15417_v1: ('http://chaiml-next-door-annoyi-15417-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Pipeline stage MKMLTemplater completed in 0.58s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-02-019-v9
Waiting for inference service junhua024-chai-02-full-02-019-v9 to be ready
Inference service junhua024-chai-02-full-02-019-v9 ready after 171.33162140846252s
Pipeline stage MKMLDeployer completed in 171.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3467817306518555s
Received healthy response to inference request in 2.085618019104004s
Received healthy response to inference request in 3.161707878112793s
Received healthy response to inference request in 1.8116731643676758s
Received healthy response to inference request in 1.5814158916473389s
5 requests
0 failed requests
5th percentile: 1.6274673461914062
10th percentile: 1.6735188007354735
20th percentile: 1.7656217098236084
30th percentile: 1.8664621353149413
40th percentile: 1.9760400772094726
50th percentile: 2.085618019104004
60th percentile: 2.5160539627075194
70th percentile: 2.946489906311035
80th percentile: 3.1987226486206053
90th percentile: 3.2727521896362304
95th percentile: 3.309766960144043
99th percentile: 3.339378776550293
mean time: 2.3974393367767335
Pipeline stage StressChecker completed in 13.43s
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 0.68s
Shutdown handler de-registered
junhua024-chai-02-full-02-019_v9 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 3388.99s
Shutdown handler de-registered
junhua024-chai-02-full-02-019_v9 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-02-019_v9 status is now torndown due to DeploymentManager action