chaiml-kimid-v4

developer_uid: chai_backend_admin

submission_id: chaiml-kimid-v4_v1

model_name: training123

model_group: ChaiML/kimid-v4

status: inactive

timestamp: 2025-12-06T16:26:29+00:00

num_battles: 5982

num_wins: 3163

celo_rating: 1311.42

family_friendly_score: 0.5102

family_friendly_standard_error: 0.007069596310964298

submission_type: basic

model_repo: ChaiML/kimid-v4

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 72

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.34919534707680117, 'latency_mean': 2.8636607229709625, 'latency_p50': 2.8689470291137695, 'latency_p90': 3.10033278465271}, {'batch_size': 2, 'throughput': 0.5341055289225881, 'latency_mean': 3.736053626537323, 'latency_p50': 3.7303532361984253, 'latency_p90': 4.022176504135132}, {'batch_size': 3, 'throughput': 0.6677284674261654, 'latency_mean': 4.4776124918460845, 'latency_p50': 4.448772549629211, 'latency_p90': 5.170033574104309}, {'batch_size': 4, 'throughput': 0.7707560741708468, 'latency_mean': 5.176356251239777, 'latency_p50': 5.166585206985474, 'latency_p90': 5.842574214935302}, {'batch_size': 5, 'throughput': 0.8350470316503388, 'latency_mean': 5.951758233308792, 'latency_p50': 5.909391403198242, 'latency_p90': 6.753131461143493}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

ineligible_reason: max_output_tokens!=64

is_internal_developer: True

language_model: ChaiML/kimid-v4

model_size: 24B

ranking_group: single

throughput_3p7s: 0.53

us_pacific_date: 2025-12-06

win_ratio: 0.5287529254429957

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', 'User:', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 72}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '####\n{bot_name}:', 'truncate_by_message': True}

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 chaiml-kimid-v4-v1-mkmlizer
Waiting for job on chaiml-kimid-v4-v1-mkmlizer to finish
chaiml-kimid-v4-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-kimid-v4-v1-mkmlizer: bash: no job control in this shell
chaiml-kimid-v4-v1-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-kimid-v4-v1-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-kimid-v4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-kimid-v4-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-kimid-v4-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-kimid-v4-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-kimid-v4-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-kimid-v4-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-kimid-v4-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-kimid-v4-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-kimid-v4-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-kimid-v4-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-v1-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-kimid-v4-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-kimid-v4-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-kimid-v4-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-kimid-v4-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-kimid-v4-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-kimid-v4-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-kimid-v4-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-kimid-v4-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-kimid-v4-v1-mkmlizer: ║                                                                     ║
chaiml-kimid-v4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-kimid-v4-v1-mkmlizer: Downloaded to shared memory in 97.687s
chaiml-kimid-v4-v1-mkmlizer: Checking if ChaiML/kimid-v4 already exists in ChaiML
chaiml-kimid-v4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_z9u82c4, device:0
chaiml-kimid-v4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-kimid-v4-v1-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:10, 30.1it/s]
Loading 0:   9%|▉         | 33.0/363 [00:01<00:10, 30.1it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:02<00:11, 27.3it/s]
Loading 0:  16%|█▋        | 59.0/363 [00:02<00:11, 27.3it/s]
Loading 0:  24%|██▎       | 86.0/363 [00:03<00:10, 27.0it/s]
Loading 0:  24%|██▎       | 86.0/363 [00:03<00:10, 27.0it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.9it/s] 
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.9it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:08, 26.6it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:08, 26.6it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.3it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 25.3it/s]
Loading 0:  52%|█████▏    | 188/363 [00:07<00:07, 24.9it/s]
Loading 0:  52%|█████▏    | 188/363 [00:07<00:07, 24.9it/s]
Loading 0:  52%|█████▏    | 188/363 [00:20<00:07, 24.9it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:37, 4.38it/s]
Loading 0:  55%|█████▌    | 201/363 [00:20<00:37, 4.38it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:23, 5.88it/s]
Loading 0:  62%|██████▏   | 224/363 [00:21<00:23, 5.88it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.52it/s]
Loading 0:  70%|███████   | 255/363 [00:22<00:12, 8.52it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:07, 10.7it/s]
Loading 0:  77%|███████▋  | 280/363 [00:23<00:07, 10.7it/s]
Loading 0:  84%|████████▍ | 306/363 [00:24<00:04, 13.0it/s]
Loading 0:  84%|████████▍ | 306/363 [00:24<00:04, 13.0it/s]
Loading 0:  93%|█████████▎| 336/363 [00:25<00:01, 15.9it/s]
Loading 0:  93%|█████████▎| 336/363 [00:25<00:01, 15.9it/s]
Loading 0: 100%|█████████▉| 362/363 [00:26<00:00, 17.8it/s]
Loading 0: 100%|█████████▉| 362/363 [00:26<00:00, 17.8it/s]
Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.8it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.4it/s]
chaiml-kimid-v4-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmp_z9u82c4' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-kimid-v4-v1-mkmlizer: quantized model in 43.993s
chaiml-kimid-v4-v1-mkmlizer: Processed model ChaiML/kimid-v4 in 141.681s
chaiml-kimid-v4-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-kimid-v4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-kimid-v4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-kimid-v4-v1/nvidia
chaiml-kimid-v4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-kimid-v4-v1/nvidia/config.json
chaiml-kimid-v4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-kimid-v4-v1/nvidia/special_tokens_map.json
chaiml-kimid-v4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-kimid-v4-v1/nvidia/tokenizer_config.json
chaiml-kimid-v4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-kimid-v4-v1/nvidia/tokenizer.json
chaiml-kimid-v4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-kimid-v4-v1/nvidia/flywheel_model.0.safetensors
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job chaiml-kimid-v4-v1-mkmlizer completed after 232.4s with status: succeeded
Stopping job with name chaiml-kimid-v4-v1-mkmlizer
Pipeline stage MKMLizer completed in 232.89s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-kimid-v4-v1
Waiting for inference service chaiml-kimid-v4-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-kimid-v4-v1 ready after 201.2767732143402s
Pipeline stage MKMLDeployer completed in 201.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.679957389831543s
Received healthy response to inference request in 2.6277923583984375s
Received healthy response to inference request in 2.758850574493408s
Received healthy response to inference request in 3.052309989929199s
Received healthy response to inference request in 2.5333242416381836s
5 requests
0 failed requests
5th percentile: 2.5522178649902343
10th percentile: 2.571111488342285
20th percentile: 2.608898735046387
30th percentile: 2.6382253646850584
40th percentile: 2.6590913772583007
50th percentile: 2.679957389831543
60th percentile: 2.7115146636962892
70th percentile: 2.743071937561035
80th percentile: 2.8175424575805663
90th percentile: 2.934926223754883
95th percentile: 2.993618106842041
99th percentile: 3.0405716133117675
mean time: 2.7304469108581544
Pipeline stage StressChecker completed in 15.39s
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 1.44s
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 0.72s
Shutdown handler de-registered
chaiml-kimid-v4_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
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2789.23s
Shutdown handler de-registered
chaiml-kimid-v4_v1 status is now inactive due to auto deactivation removed underperforming models