developer_uid: rirv938
submission_id: chaiml-96p-4ff-chaiml-m_19791_v2
model_name: chaiml-96p-4ff-chaiml-m_19791_v2
model_group: ChaiML/96p_4ff_chaiml_mi
status: torndown
timestamp: 2026-01-29T16:38:37+00:00
num_battles: 11314
num_wins: 6163
celo_rating: 1337.12
family_friendly_score: 0.5126
family_friendly_standard_error: 0.007068822249851809
submission_type: basic
model_repo: ChaiML/96p_4ff_chaiml_mistral_24b_2048_63507_v3_cp624_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 96
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3435779296533457, 'latency_mean': 2.910484012365341, 'latency_p50': 2.8952921628952026, 'latency_p90': 3.120973801612854}, {'batch_size': 2, 'throughput': 0.5334064153135218, 'latency_mean': 3.749425517320633, 'latency_p50': 3.7531439065933228, 'latency_p90': 3.9643545150756836}, {'batch_size': 3, 'throughput': 0.6714998880194195, 'latency_mean': 4.4548349130153655, 'latency_p50': 4.4485379457473755, 'latency_p90': 4.759388446807861}, {'batch_size': 4, 'throughput': 0.7658897957434231, 'latency_mean': 5.201523947715759, 'latency_p50': 5.1795936822891235, 'latency_p90': 5.8534095764160154}, {'batch_size': 5, 'throughput': 0.82664321987111, 'latency_mean': 6.018506730794907, 'latency_p50': 5.9867459535598755, 'latency_p90': 6.709308815002442}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-96p-4ff-chaiml-m_19791_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/96p_4ff_chaiml_mistral_24b_2048_63507_v3_cp624_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 0.52
us_pacific_date: 2026-01-19
win_ratio: 0.5447233515997879
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['###', '</s>', '<|im_start|>', 'You:', '<|im_end|>', '\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 96}
formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer
Waiting for job on chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer to finish
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: bash: no job control in this shell
chaiml-96p-4ff-chaiml-m-19791-v2-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-96p-4ff-chaiml-m-19791-v2-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║                                                                     ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║                                                                     ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║                                                                     ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║                                                                     ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ║                                                                     ║
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: Downloaded to shared memory in 90.426s
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: Checking if ChaiML/96p_4ff_chaiml_mistral_24b_2048_63507_v3_cp624_merged already exists in ChaiML
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpn96ag5bl, device:0
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: The tokenizer you are loading from '/tmp/tmpn96ag5bl' 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-96p-4ff-chaiml-m-19791-v2-mkmlizer: quantized model in 282.549s
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: Processed model ChaiML/96p_4ff_chaiml_mistral_24b_2048_63507_v3_cp624_merged in 372.976s
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-96p-4ff-chaiml-m-19791-v2/nvidia
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-96p-4ff-chaiml-m-19791-v2/nvidia/config.json
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-96p-4ff-chaiml-m-19791-v2/nvidia/special_tokens_map.json
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-96p-4ff-chaiml-m-19791-v2/nvidia/tokenizer_config.json
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-96p-4ff-chaiml-m-19791-v2/nvidia/tokenizer.json
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-96p-4ff-chaiml-m-19791-v2/nvidia/flywheel_model.1.safetensors
chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-96p-4ff-chaiml-m-19791-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer completed after 465.39s with status: succeeded
Stopping job with name chaiml-96p-4ff-chaiml-m-19791-v2-mkmlizer
Pipeline stage MKMLizer completed in 466.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.24s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-96p-4ff-chaiml-m-19791-v2
Waiting for inference service chaiml-96p-4ff-chaiml-m-19791-v2 to be ready
Inference service chaiml-96p-4ff-chaiml-m-19791-v2 ready after 223.25729179382324s
Pipeline stage MKMLDeployer completed in 224.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.93210768699646s
Received healthy response to inference request in 2.8710520267486572s
Received healthy response to inference request in 2.851492404937744s
Received healthy response to inference request in 2.594639778137207s
Received healthy response to inference request in 2.531559705734253s
5 requests
0 failed requests
5th percentile: 2.544175720214844
10th percentile: 2.5567917346954347
20th percentile: 2.582023763656616
30th percentile: 2.6460103034973144
40th percentile: 2.7487513542175295
50th percentile: 2.851492404937744
60th percentile: 2.8593162536621093
70th percentile: 2.8671401023864744
80th percentile: 2.8832631587982176
90th percentile: 2.907685422897339
95th percentile: 2.9198965549468996
99th percentile: 2.929665460586548
mean time: 2.756170320510864
Pipeline stage StressChecker completed in 15.72s
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 0.98s
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 1.04s
Shutdown handler de-registered
chaiml-96p-4ff-chaiml-m_19791_v2 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-96p-4ff-chaiml-m-19791-v2-profiler
Waiting for inference service chaiml-96p-4ff-chaiml-m-19791-v2-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
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2779.43s
Shutdown handler de-registered
chaiml-96p-4ff-chaiml-m_19791_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-96p-4ff-chaiml-m_19791_v2 status is now protected due to ABTestQueueItem
chaiml-96p-4ff-chaiml-m_19791_v2 status is now inactive due to ABTestQueueItem
chaiml-96p-4ff-chaiml-m_19791_v2 status is now torndown due to DeploymentManager action