chaiml-2fe5-c13f-linear-w01

developer_uid: rirv938

submission_id: chaiml-2fe5-c13f-linear-w01_v31

model_name: chaiml-2fe5-c13f-linear-w01_v31

model_group: ChaiML/2fe5-c13f-linear-

status: inactive

timestamp: 2025-12-09T22:24:52+00:00

num_battles: 8162

num_wins: 4018

celo_rating: 1288.09

family_friendly_score: 0.552

family_friendly_standard_error: 0.007032723512267492

submission_type: basic

model_repo: ChaiML/2fe5-c13f-linear-w01

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.7047375303109161, 'latency_mean': 1.4189031386375428, 'latency_p50': 1.4127477407455444, 'latency_p90': 1.5732110738754272}, {'batch_size': 4, 'throughput': 1.5842877125084447, 'latency_mean': 2.514640463590622, 'latency_p50': 2.511702299118042, 'latency_p90': 2.834396910667419}, {'batch_size': 5, 'throughput': 1.735286749759488, 'latency_mean': 2.8688701438903808, 'latency_p50': 2.8647865056991577, 'latency_p90': 3.2292837381362913}, {'batch_size': 8, 'throughput': 2.0410588253488218, 'latency_mean': 3.8866423535346986, 'latency_p50': 3.8777793645858765, 'latency_p90': 4.499710965156555}, {'batch_size': 10, 'throughput': 2.1439706645920626, 'latency_mean': 4.628558548688889, 'latency_p50': 4.607583522796631, 'latency_p90': 5.346503400802613}, {'batch_size': 12, 'throughput': 2.2304766151410824, 'latency_mean': 5.320161341428757, 'latency_p50': 5.317485570907593, 'latency_p90': 6.182736110687255}, {'batch_size': 15, 'throughput': 2.3215841671996427, 'latency_mean': 6.390260385274887, 'latency_p50': 6.376248240470886, 'latency_p90': 7.525559878349304}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-2fe5-c13f-linear-w01_v31

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: ChaiML/2fe5-c13f-linear-w01

model_size: 13B

ranking_group: single

throughput_3p7s: 2.01

us_pacific_date: 2025-12-08

win_ratio: 0.4922813036020583

generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['You:', '</s>', 'Bot:', '\n', '####', '<|eot_id|>', '<|im_end|>', 'User:'], 'max_input_tokens': 2048, 'best_of': 4, 'max_output_tokens': 64}

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': '{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-2fe5-c13f-linear-w01-v31-mkmlizer
Waiting for job on chaiml-2fe5-c13f-linear-w01-v31-mkmlizer to finish
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: bash: no job control in this shell
chaiml-2fe5-c13f-linear-w01-v31-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-2fe5-c13f-linear-w01-v31-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  belonging to:                                                      ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ║                                                                     ║
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: Downloaded to shared memory in 29.072s
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: Checking if ChaiML/2fe5-c13f-linear-w01 already exists in ChaiML
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpklyyohmp, device:0
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: 
Loading 0:   0%|          | 0.00/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2.00/363 [00:05<15:41, 2.61s/it]
Loading 0:   1%|          | 2.00/363 [00:05<15:41, 2.61s/it]
Loading 0:  11%|█         | 40.0/363 [00:06<00:39, 8.19it/s]
Loading 0:  11%|█         | 40.0/363 [00:06<00:39, 8.19it/s]
Loading 0:  21%|██▏       | 78.0/363 [00:07<00:19, 14.9it/s]
Loading 0:  21%|██▏       | 78.0/363 [00:07<00:19, 14.9it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:11, 21.1it/s] 
Loading 0:  33%|███▎      | 121/363 [00:08<00:11, 21.1it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:07, 26.3it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:07, 26.3it/s]
Loading 0:  56%|█████▌    | 202/363 [00:10<00:05, 29.0it/s]
Loading 0:  56%|█████▌    | 202/363 [00:10<00:05, 29.0it/s]
Loading 0:  67%|██████▋   | 243/363 [00:11<00:03, 32.3it/s]
Loading 0:  67%|██████▋   | 243/363 [00:11<00:03, 32.3it/s]
Loading 0:  78%|███████▊  | 283/363 [00:12<00:02, 33.2it/s]
Loading 0:  78%|███████▊  | 283/363 [00:12<00:02, 33.2it/s]
Loading 0:  88%|████████▊ | 321/363 [00:13<00:01, 34.4it/s]
Loading 0:  88%|████████▊ | 321/363 [00:13<00:01, 34.4it/s]
Loading 0: 100%|██████████| 363/363 [00:14<00:00, 36.4it/s]
Loading 0: 100%|██████████| 363/363 [00:14<00:00, 36.4it/s]
                                                           

Loading 0: 100%|██████████| 363/363 [00:14<00:00, 24.5it/s]
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: The tokenizer you are loading from '/tmp/tmpklyyohmp' 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-2fe5-c13f-linear-w01-v31-mkmlizer: quantized model in 27.851s
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: Processed model ChaiML/2fe5-c13f-linear-w01 in 56.924s
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: creating bucket guanaco-mkml-models
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v31/nvidia
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v31/nvidia/config.json
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/chat_template.jinja s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v31/nvidia/chat_template.jinja
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v31/nvidia/special_tokens_map.json
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v31/nvidia/tokenizer_config.json
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v31/nvidia/tokenizer.json
chaiml-2fe5-c13f-linear-w01-v31-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-2fe5-c13f-linear-w01-v31/nvidia/flywheel_model.0.safetensors
Job chaiml-2fe5-c13f-linear-w01-v31-mkmlizer completed after 114.0s with status: succeeded
Stopping job with name chaiml-2fe5-c13f-linear-w01-v31-mkmlizer
Pipeline stage MKMLizer completed in 114.48s
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-2fe5-c13f-linear-w01-v31
Waiting for inference service chaiml-2fe5-c13f-linear-w01-v31 to be ready
Failed to get response for submission blend_talus_2025-12-08: HTTPConnectionPool(host='chaiml-4d70-fd43-linear-w01-v17-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-2fe5-c13f-linear-w01-v31 ready after 211.17846083641052s
Pipeline stage MKMLDeployer completed in 211.76s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5600814819335938s
Received healthy response to inference request in 1.2893521785736084s
Received healthy response to inference request in 1.4883041381835938s
Received healthy response to inference request in 1.594428539276123s
Received healthy response to inference request in 1.483665943145752s
5 requests
0 failed requests
5th percentile: 1.3282149314880372
10th percentile: 1.367077684402466
20th percentile: 1.4448031902313232
30th percentile: 1.4845935821533203
40th percentile: 1.4864488601684571
50th percentile: 1.4883041381835938
60th percentile: 1.5170150756835938
70th percentile: 1.5457260131835937
80th percentile: 1.5669508934020997
90th percentile: 1.5806897163391114
95th percentile: 1.587559127807617
99th percentile: 1.5930546569824218
mean time: 1.4831664562225342
Pipeline stage StressChecker completed in 8.71s
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 0.64s
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 0.66s
Shutdown handler de-registered
chaiml-2fe5-c13f-linear-w01_v31 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-2fe5-c13f-linear-w01-v31-profiler
Waiting for inference service chaiml-2fe5-c13f-linear-w01-v31-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 1691.36s
Shutdown handler de-registered
chaiml-2fe5-c13f-linear-w01_v31 status is now inactive due to auto deactivation removed underperforming models
chaiml-2fe5-c13f-linear-w01_v31 status is now protected due to ABTestQueueItem