developer_uid: junhua024
submission_id: junhua024-chai-19nn1_v1
model_name: junhua024-chai-19nn1_v1
model_group: junhua024/chai_19nn1
status: torndown
timestamp: 2025-07-28T18:26:15+00:00
num_battles: 5421
num_wins: 2723
celo_rating: 1275.67
family_friendly_score: 0.5187999999999999
family_friendly_standard_error: 0.007066067647567492
submission_type: basic
model_repo: junhua024/chai_19nn1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: junhua024-chai-19nn1_v1
is_internal_developer: False
language_model: junhua024/chai_19nn1
model_size: 13B
ranking_group: single
us_pacific_date: 2025-07-28
win_ratio: 0.5023058476295886
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': 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-19nn1-v1-mkmlizer
Waiting for job on junhua024-chai-19nn1-v1-mkmlizer to finish
junhua024-chai-19nn1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-19nn1-v1-mkmlizer: ║                                                                     ║
junhua024-chai-19nn1-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-19nn1-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-19nn1-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-19nn1-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-19nn1-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-19nn1-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-19nn1-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-19nn1-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-19nn1-v1-mkmlizer: ║                                                                     ║
junhua024-chai-19nn1-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-19nn1-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-19nn1-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-19nn1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-19nn1-v1-mkmlizer: ║                                                                     ║
junhua024-chai-19nn1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-19nn1-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-19nn1-v1-mkmlizer: ║                                                                     ║
junhua024-chai-19nn1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-19nn1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-19nn1-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-19nn1-v1-mkmlizer: ║                                                                     ║
junhua024-chai-19nn1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-19nn1-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-19nn1-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 junhua024-chai-12-full-20-2_v1: HTTPConnectionPool(host='junhua024-chai-12-full-20-2-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-19nn1-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-19nn1-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 junhua024-chai-12-full-20_v5: HTTPConnectionPool(host='junhua024-chai-12-full-20-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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 junhua024-chai-19cl-full-0022_v7: HTTPConnectionPool(host='junhua024-chai-19cl-full-0022-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-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-19nn1-v1-mkmlizer: Downloaded to shared memory in 155.252s
junhua024-chai-19nn1-v1-mkmlizer: Checking if junhua024/chai_19nn1 already exists in ChaiML
junhua024-chai-19nn1-v1-mkmlizer: Creating repo ChaiML/chai_19nn1 and uploading /tmp/tmphsbgoc4g to it
junhua024-chai-19nn1-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:02<01:02,  2.49s/it]
  8%|▊         | 2/26 [00:04<00:47,  1.97s/it]
 12%|█▏        | 3/26 [00:05<00:41,  1.80s/it]
 15%|█▌        | 4/26 [00:08<00:47,  2.16s/it]
 19%|█▉        | 5/26 [00:11<00:52,  2.51s/it]
 23%|██▎       | 6/26 [00:13<00:43,  2.18s/it]
 27%|██▋       | 7/26 [00:14<00:39,  2.07s/it]
 31%|███       | 8/26 [00:16<00:35,  1.99s/it]
 35%|███▍      | 9/26 [00:18<00:31,  1.83s/it]
 38%|███▊      | 10/26 [00:20<00:32,  2.01s/it]
 42%|████▏     | 11/26 [00:22<00:29,  1.95s/it]
 46%|████▌     | 12/26 [00:24<00:25,  1.85s/it]
 50%|█████     | 13/26 [00:25<00:22,  1.71s/it]
 54%|█████▍    | 14/26 [00:26<00:19,  1.65s/it]
 58%|█████▊    | 15/26 [00:28<00:18,  1.71s/it]
 62%|██████▏   | 16/26 [00:30<00:16,  1.69s/it]
 65%|██████▌   | 17/26 [00:32<00:15,  1.77s/it]
 69%|██████▉   | 18/26 [00:34<00:16,  2.01s/it]
 73%|███████▎  | 19/26 [00:36<00:13,  1.91s/it]
 77%|███████▋  | 20/26 [00:38<00:11,  1.84s/it]
 81%|████████  | 21/26 [00:39<00:08,  1.71s/it]
 85%|████████▍ | 22/26 [00:41<00:06,  1.65s/it]
 88%|████████▊ | 23/26 [00:43<00:05,  1.71s/it]
 92%|█████████▏| 24/26 [00:45<00:03,  1.97s/it]
 96%|█████████▌| 25/26 [00:46<00:01,  1.78s/it]
100%|██████████| 26/26 [00:48<00:00,  1.59s/it]
100%|██████████| 26/26 [00:48<00:00,  1.85s/it]
junhua024-chai-19nn1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmphsbgoc4g, device:0
junhua024-chai-19nn1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission junhua024-chai-12-full-20_v5: HTTPConnectionPool(host='junhua024-chai-12-full-20-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-19nn1-v1-mkmlizer: quantized model in 164.675s
junhua024-chai-19nn1-v1-mkmlizer: Processed model junhua024/chai_19nn1 in 411.970s
junhua024-chai-19nn1-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-19nn1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-19nn1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-19nn1-v1/nvidia
junhua024-chai-19nn1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-19nn1-v1/nvidia/special_tokens_map.json
junhua024-chai-19nn1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-19nn1-v1/nvidia/config.json
junhua024-chai-19nn1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-19nn1-v1/nvidia/tokenizer_config.json
junhua024-chai-19nn1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-19nn1-v1/nvidia/tokenizer.json
junhua024-chai-19nn1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-19nn1-v1/nvidia/flywheel_model.0.safetensors
Failed to get response for submission junhua024-chai-19cl-full-0022_v7: HTTPConnectionPool(host='junhua024-chai-19cl-full-0022-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-12-full-20-2_v1: HTTPConnectionPool(host='junhua024-chai-12-full-20-2-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Job junhua024-chai-19nn1-v1-mkmlizer completed after 439.57s with status: succeeded
Stopping job with name junhua024-chai-19nn1-v1-mkmlizer
Pipeline stage MKMLizer completed in 440.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-19nn1-v1
Waiting for inference service junhua024-chai-19nn1-v1 to be ready
Failed to get response for submission junhua024-chai-19cl-full-0022_v7: HTTPConnectionPool(host='junhua024-chai-19cl-full-0022-v7-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)
Failed to get response for submission junhua024-chai-12-full-20_v5: HTTPConnectionPool(host='junhua024-chai-12-full-20-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-19nn1-v1 ready after 311.19339776039124s
Pipeline stage MKMLDeployer completed in 311.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6803689002990723s
Received healthy response to inference request in 2.0301930904388428s
Received healthy response to inference request in 2.454643726348877s
Received healthy response to inference request in 2.3236849308013916s
Received healthy response to inference request in 1.6964473724365234s
5 requests
0 failed requests
5th percentile: 1.7631965160369873
10th percentile: 1.8299456596374513
20th percentile: 1.9634439468383789
30th percentile: 2.0888914585113527
40th percentile: 2.206288194656372
50th percentile: 2.3236849308013916
60th percentile: 2.376068449020386
70th percentile: 2.42845196723938
80th percentile: 2.499788761138916
90th percentile: 2.590078830718994
95th percentile: 2.635223865509033
99th percentile: 2.6713398933410644
mean time: 2.2370676040649413
Pipeline stage StressChecker completed in 12.85s
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 0.82s
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 0.77s
Shutdown handler de-registered
junhua024-chai-19nn1_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-19nn1-v1-profiler
Waiting for inference service junhua024-chai-19nn1-v1-profiler to be ready
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 2876.41s
Shutdown handler de-registered
junhua024-chai-19nn1_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-19nn1_v1 status is now torndown due to DeploymentManager action