junhua024-chai-12-full-06-06

developer_uid: junhua024
submission_id: junhua024-chai-12-full-06-06_v1
model_name: junhua024-chai-12-full-06-06_v1
model_group: junhua024/chai_12_full_0
status: torndown
timestamp: 2025-07-27T09:34:56+00:00
num_battles: 5644
num_wins: 2120
celo_rating: 1158.35
family_friendly_score: 0.6464
family_friendly_standard_error: 0.006761169129669809
submission_type: basic
model_repo: junhua024/chai_12_full_06_06
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
display_name: junhua024-chai-12-full-06-06_v1
is_internal_developer: False
language_model: junhua024/chai_12_full_06_06
model_size: 13B
ranking_group: single
us_pacific_date: 2025-07-27
win_ratio: 0.3756201275690999
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "You are an empathetic conversational AI. You understand the user's feelings and respond with warmth, compassion, and sincerity. Each of your responses should be fewer than 64 tokens long.", '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-12-full-06-06-v1-mkmlizer
Waiting for job on junhua024-chai-12-full-06-06-v1-mkmlizer to finish
junhua024-chai-12-full-06-06-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-12-full-06-06-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-06-06-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-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-12-full-06-06-v1-mkmlizer: Downloaded to shared memory in 117.340s
junhua024-chai-12-full-06-06-v1-mkmlizer: Checking if junhua024/chai_12_full_06_06 already exists in ChaiML
junhua024-chai-12-full-06-06-v1-mkmlizer: Creating repo ChaiML/chai_12_full_06_06 and uploading /tmp/tmpucss4os9 to it
junhua024-chai-12-full-06-06-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:06<02:38,  6.34s/it]
  8%|▊         | 2/26 [00:07<01:20,  3.34s/it]
 12%|█▏        | 3/26 [00:09<00:57,  2.50s/it]
 15%|█▌        | 4/26 [00:10<00:45,  2.05s/it]
 19%|█▉        | 5/26 [00:11<00:36,  1.75s/it]
 23%|██▎       | 6/26 [00:12<00:31,  1.58s/it]
 27%|██▋       | 7/26 [00:14<00:27,  1.46s/it]
 31%|███       | 8/26 [00:15<00:25,  1.40s/it]
 35%|███▍      | 9/26 [00:17<00:26,  1.58s/it]
 38%|███▊      | 10/26 [00:19<00:26,  1.63s/it]
 42%|████▏     | 11/26 [00:20<00:23,  1.56s/it]
 46%|████▌     | 12/26 [00:23<00:26,  1.89s/it]
 50%|█████     | 13/26 [00:25<00:25,  1.95s/it]
 54%|█████▍    | 14/26 [00:29<00:30,  2.56s/it]
 58%|█████▊    | 15/26 [00:30<00:24,  2.21s/it]
 62%|██████▏   | 16/26 [00:31<00:19,  1.91s/it]
 65%|██████▌   | 17/26 [00:33<00:16,  1.88s/it]
 69%|██████▉   | 18/26 [00:34<00:13,  1.70s/it]
 73%|███████▎  | 19/26 [00:36<00:12,  1.75s/it]
 77%|███████▋  | 20/26 [00:37<00:09,  1.58s/it]
 81%|████████  | 21/26 [00:39<00:08,  1.65s/it]
 85%|████████▍ | 22/26 [00:41<00:06,  1.53s/it]
 88%|████████▊ | 23/26 [00:42<00:04,  1.51s/it]
 92%|█████████▏| 24/26 [00:43<00:02,  1.49s/it]
 96%|█████████▌| 25/26 [00:45<00:01,  1.49s/it]
100%|██████████| 26/26 [00:46<00:00,  1.39s/it]
100%|██████████| 26/26 [00:46<00:00,  1.79s/it]
junhua024-chai-12-full-06-06-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpucss4os9, device:0
junhua024-chai-12-full-06-06-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-12-full-06-06-v1-mkmlizer: quantized model in 161.813s
junhua024-chai-12-full-06-06-v1-mkmlizer: Processed model junhua024/chai_12_full_06_06 in 362.442s
junhua024-chai-12-full-06-06-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-12-full-06-06-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-12-full-06-06-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-12-full-06-06-v1/nvidia
junhua024-chai-12-full-06-06-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-12-full-06-06-v1/nvidia/config.json
junhua024-chai-12-full-06-06-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-12-full-06-06-v1/nvidia/special_tokens_map.json
junhua024-chai-12-full-06-06-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-12-full-06-06-v1/nvidia/tokenizer_config.json
junhua024-chai-12-full-06-06-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-12-full-06-06-v1/nvidia/tokenizer.json
Job junhua024-chai-12-full-06-06-v1-mkmlizer completed after 388.08s with status: succeeded
Stopping job with name junhua024-chai-12-full-06-06-v1-mkmlizer
Pipeline stage MKMLizer completed in 388.66s
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-12-full-06-06-v1
Waiting for inference service junhua024-chai-12-full-06-06-v1 to be ready
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', '')
Failed to get response for submission chaiml-gy-exp236-sft-gy_30367_v1: HTTPConnectionPool(host='chaiml-gy-exp236-sft-gy-30367-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
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', '')
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', '')
Inference service junhua024-chai-12-full-06-06-v1 ready after 191.879549741745s
Pipeline stage MKMLDeployer completed in 192.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4112792015075684s
Received healthy response to inference request in 0.5910501480102539s
Received healthy response to inference request in 0.567582368850708s
Received healthy response to inference request in 1.722815990447998s
Received healthy response to inference request in 1.7801227569580078s
5 requests
0 failed requests
5th percentile: 0.5722759246826172
10th percentile: 0.5769694805145263
20th percentile: 0.5863565921783447
30th percentile: 0.8174033164978027
40th percentile: 1.2701096534729004
50th percentile: 1.722815990447998
60th percentile: 1.745738697052002
70th percentile: 1.7686614036560058
80th percentile: 2.10635404586792
90th percentile: 2.7588166236877445
95th percentile: 3.085047912597656
99th percentile: 3.346032943725586
mean time: 1.6145700931549072
Pipeline stage StressChecker completed in 10.17s
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 1.08s
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 1.00s
Shutdown handler de-registered
junhua024-chai-12-full-06-06_v1 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 2591.40s
Shutdown handler de-registered
junhua024-chai-12-full-06-06_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-12-full-06-06_v1 status is now torndown due to DeploymentManager action