junhua024-chai-12-full-22

developer_uid: junhua024
submission_id: junhua024-chai-12-full-22_v1
model_name: junhua024-chai-12-full-22_v1
model_group: junhua024/chai_12_full_2
status: torndown
timestamp: 2025-07-28T10:52:36+00:00
num_battles: 7998
num_wins: 4168
celo_rating: 1276.4
family_friendly_score: 0.569
family_friendly_standard_error: 0.007003413453452538
submission_type: basic
model_repo: junhua024/chai_12_full_22
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-22_v1
is_internal_developer: False
language_model: junhua024/chai_12_full_22
model_size: 13B
ranking_group: single
us_pacific_date: 2025-07-28
win_ratio: 0.5211302825706426
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-22-v1-mkmlizer
Waiting for job on junhua024-chai-12-full-22-v1-mkmlizer to finish
junhua024-chai-12-full-22-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-12-full-22-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-22-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-12-full-22-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-12-full-22-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-12-full-22-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-12-full-22-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-12-full-22-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-12-full-22-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-12-full-22-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-12-full-22-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-12-full-22-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-12-full-22-v1-mkmlizer: ║                                                                     ║
junhua024-chai-12-full-22-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-12-full-22-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-22-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-22-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-22-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-22-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-22-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-22-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`
Failed to get response for submission chaiml-gy-exp241-sft-gy-_3670_v1: HTTPConnectionPool(host='chaiml-gy-exp241-sft-gy-3670-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-12-full-22-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-22-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-22-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-22-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`
Failed to get response for submission chaiml-gy-exp241-sft-gy-_3670_v1: HTTPConnectionPool(host='chaiml-gy-exp241-sft-gy-3670-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-12-full-22-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-22-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-22-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-22-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-22-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-22-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-22-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-22-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-22-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-22-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-22-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-22-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-22-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-22-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-22-v1-mkmlizer: Downloaded to shared memory in 131.274s
junhua024-chai-12-full-22-v1-mkmlizer: Checking if junhua024/chai_12_full_22 already exists in ChaiML
junhua024-chai-12-full-22-v1-mkmlizer: Creating repo ChaiML/chai_12_full_22 and uploading /tmp/tmp3il42he3 to it
junhua024-chai-12-full-22-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:02<00:51,  2.05s/it]
  8%|▊         | 2/26 [00:03<00:43,  1.82s/it]
 12%|█▏        | 3/26 [00:05<00:41,  1.82s/it]
 15%|█▌        | 4/26 [00:07<00:39,  1.80s/it]
 19%|█▉        | 5/26 [00:13<01:12,  3.45s/it]
 23%|██▎       | 6/26 [00:15<00:57,  2.88s/it]
 27%|██▋       | 7/26 [00:17<00:52,  2.75s/it]
 31%|███       | 8/26 [00:19<00:43,  2.40s/it]
 35%|███▍      | 9/26 [00:21<00:39,  2.30s/it]
 38%|███▊      | 10/26 [00:23<00:32,  2.06s/it]
 42%|████▏     | 11/26 [00:24<00:29,  1.96s/it]
 46%|████▌     | 12/26 [00:26<00:26,  1.86s/it]
 50%|█████     | 13/26 [00:31<00:35,  2.69s/it]
 54%|█████▍    | 14/26 [00:32<00:28,  2.35s/it]
 58%|█████▊    | 15/26 [00:34<00:22,  2.09s/it]
 62%|██████▏   | 16/26 [00:35<00:19,  1.93s/it]
 65%|██████▌   | 17/26 [00:37<00:16,  1.82s/it]
 69%|██████▉   | 18/26 [00:38<00:13,  1.72s/it]
 73%|███████▎  | 19/26 [00:40<00:11,  1.68s/it]
 77%|███████▋  | 20/26 [00:41<00:09,  1.63s/it]
 81%|████████  | 21/26 [00:43<00:07,  1.58s/it]
 85%|████████▍ | 22/26 [00:44<00:06,  1.58s/it]
 88%|████████▊ | 23/26 [00:46<00:04,  1.56s/it]
 92%|█████████▏| 24/26 [00:49<00:03,  1.95s/it]
 96%|█████████▌| 25/26 [00:51<00:01,  1.88s/it]
100%|██████████| 26/26 [00:52<00:00,  1.70s/it]
100%|██████████| 26/26 [00:52<00:00,  2.01s/it]
junhua024-chai-12-full-22-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp3il42he3, device:0
junhua024-chai-12-full-22-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission junhua024-chai-12-full-19_v2: HTTPConnectionPool(host='junhua024-chai-12-full-19-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-gy-exp241-sft-gy-_3670_v1: HTTPConnectionPool(host='chaiml-gy-exp241-sft-gy-3670-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-12-full-22-v1-mkmlizer: quantized model in 166.558s
junhua024-chai-12-full-22-v1-mkmlizer: Processed model junhua024/chai_12_full_22 in 370.501s
junhua024-chai-12-full-22-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-12-full-22-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-12-full-22-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-12-full-22-v1/nvidia
junhua024-chai-12-full-22-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-12-full-22-v1/nvidia/config.json
junhua024-chai-12-full-22-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-12-full-22-v1/nvidia/special_tokens_map.json
junhua024-chai-12-full-22-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-12-full-22-v1/nvidia/tokenizer_config.json
junhua024-chai-12-full-22-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-12-full-22-v1/nvidia/tokenizer.json
junhua024-chai-12-full-22-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-12-full-22-v1/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-12-full-22-v1-mkmlizer completed after 399.17s with status: succeeded
Stopping job with name junhua024-chai-12-full-22-v1-mkmlizer
Pipeline stage MKMLizer completed in 399.73s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.59s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-12-full-22-v1
Waiting for inference service junhua024-chai-12-full-22-v1 to be ready
Inference service junhua024-chai-12-full-22-v1 ready after 220.98710203170776s
Pipeline stage MKMLDeployer completed in 221.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1542611122131348s
Received healthy response to inference request in 2.01747465133667s
Received healthy response to inference request in 1.3781585693359375s
Received healthy response to inference request in 1.5553133487701416s
Received healthy response to inference request in 1.426297664642334s
5 requests
0 failed requests
5th percentile: 1.3877863883972168
10th percentile: 1.397414207458496
20th percentile: 1.4166698455810547
30th percentile: 1.4521008014678956
40th percentile: 1.5037070751190185
50th percentile: 1.5553133487701416
60th percentile: 1.740177869796753
70th percentile: 1.9250423908233643
80th percentile: 2.044831943511963
90th percentile: 2.099546527862549
95th percentile: 2.1269038200378416
99th percentile: 2.148789653778076
mean time: 1.7063010692596436
Pipeline stage StressChecker completed in 9.83s
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 0.71s
Shutdown handler de-registered
junhua024-chai-12-full-22_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5712.04s
Shutdown handler de-registered
junhua024-chai-12-full-22_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-12-full-22_v1 status is now torndown due to DeploymentManager action