developer_uid: chai_backend_admin
submission_id: chaiml-leon-mc-rge-leon_62013_v1
model_name: chaiml-leon-mc-rge-leon_62013_v1
model_group: ChaiML/Leon-MC-RGE_Leon-
status: inactive
timestamp: 2026-01-26T01:47:04+00:00
num_battles: 10631
num_wins: 4928
celo_rating: 1278.99
family_friendly_score: 0.4718
family_friendly_standard_error: 0.007059812462098409
submission_type: basic
model_repo: ChaiML/Leon-MC-RGE_Leon-MC-RGE260126001746_sft
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.440145232131215, 'latency_mean': 2.271899049282074, 'latency_p50': 2.277153491973877, 'latency_p90': 2.5131686210632322}, {'batch_size': 3, 'throughput': 0.930373468485491, 'latency_mean': 3.216103831529617, 'latency_p50': 3.2262179851531982, 'latency_p90': 3.527040123939514}, {'batch_size': 5, 'throughput': 1.2303556074415356, 'latency_mean': 4.041045196056366, 'latency_p50': 4.022637605667114, 'latency_p90': 4.564034533500672}, {'batch_size': 6, 'throughput': 1.3408236316584694, 'latency_mean': 4.451216453313828, 'latency_p50': 4.417947769165039, 'latency_p90': 5.049374413490296}, {'batch_size': 8, 'throughput': 1.5116380839500454, 'latency_mean': 5.2635800385475155, 'latency_p50': 5.310766696929932, 'latency_p90': 5.986808800697327}, {'batch_size': 10, 'throughput': 1.5957767469864652, 'latency_mean': 6.213820152282715, 'latency_p50': 6.194328665733337, 'latency_p90': 7.07882342338562}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-leon-mc-rge-leon_62013_v1
is_internal_developer: True
language_model: ChaiML/Leon-MC-RGE_Leon-MC-RGE260126001746_sft
model_size: 24B
ranking_group: single
throughput_3p7s: 1.13
us_pacific_date: 2026-01-25
win_ratio: 0.4635499952967736
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', '\n', 'You:', '</s>', '####'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {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
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
Starting job with name chaiml-leon-mc-rge-leon-62013-v1-mkmlizer
Waiting for job on chaiml-leon-mc-rge-leon-62013-v1-mkmlizer to finish
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: bash: no job control in this shell
chaiml-leon-mc-rge-leon-62013-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-leon-mc-rge-leon-62013-v1-mkmlizer: __import__('pkg_resources').declare_namespace(__name__)
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ Version: 0.30.6+torch280 ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ belonging to: ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ║ ║
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: Loading 0: 0%| | 0.00/363 [00:00<?, ?it/s] Loading 0: 8%|▊ | 28.0/363 [00:00<00:11, 29.3it/s] Loading 0: 8%|▊ | 28.0/363 [00:00<00:11, 29.3it/s] Loading 0: 14%|█▍ | 50.0/363 [00:01<00:12, 24.7it/s] Loading 0: 14%|█▍ | 50.0/363 [00:01<00:12, 24.7it/s] Loading 0: 21%|██▏ | 78.0/363 [00:03<00:11, 25.5it/s] Loading 0: 21%|██▏ | 78.0/363 [00:03<00:11, 25.5it/s] Loading 0: 29%|██▉ | 105/363 [00:04<00:09, 26.0it/s] Loading 0: 29%|██▉ | 105/363 [00:04<00:09, 26.0it/s] Loading 0: 36%|███▌ | 130/363 [00:05<00:09, 25.4it/s] Loading 0: 36%|███▌ | 130/363 [00:05<00:09, 25.4it/s] Loading 0: 42%|████▏ | 153/363 [00:06<00:08, 24.1it/s] Loading 0: 42%|████▏ | 153/363 [00:06<00:08, 24.1it/s] Loading 0: 49%|████▉ | 179/363 [00:07<00:07, 24.7it/s] Loading 0: 49%|████▉ | 179/363 [00:07<00:07, 24.7it/s] Loading 0: 49%|████▉ | 179/363 [00:21<00:07, 24.7it/s] Loading 0: 55%|█████▌ | 201/363 [00:21<00:34, 4.72it/s] Loading 0: 55%|█████▌ | 201/363 [00:21<00:34, 4.72it/s] Loading 0: 62%|██████▏ | 224/363 [00:22<00:22, 6.14it/s] Loading 0: 62%|██████▏ | 224/363 [00:22<00:22, 6.14it/s] Loading 0: 70%|███████ | 255/363 [00:23<00:12, 8.67it/s] Loading 0: 70%|███████ | 255/363 [00:23<00:12, 8.67it/s] Loading 0: 77%|███████▋ | 280/363 [00:24<00:07, 10.7it/s] Loading 0: 77%|███████▋ | 280/363 [00:24<00:07, 10.7it/s] Loading 0: 84%|████████▍ | 306/363 [00:25<00:04, 12.8it/s] Loading 0: 84%|████████▍ | 306/363 [00:25<00:04, 12.8it/s] Loading 0: 93%|█████████▎| 336/363 [00:26<00:01, 15.5it/s] Loading 0: 93%|█████████▎| 336/363 [00:26<00:01, 15.5it/s] Loading 0: 99%|█████████▉| 360/363 [00:27<00:00, 17.2it/s] Loading 0: 99%|█████████▉| 360/363 [00:27<00:00, 17.2it/s] Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.3it/s] Loading 0: 100%|██████████| 363/363 [00:27<00:00, 17.3it/s] Loading 0: 100%|██████████| 363/363 [00:27<00:00, 13.1it/s]
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: The tokenizer you are loading from '/tmp/tmpqzhy1k2g' 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-leon-mc-rge-leon-62013-v1-mkmlizer: quantized model in 44.773s
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: Processed model ChaiML/Leon-MC-RGE_Leon-MC-RGE260126001746_sft in 130.273s
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-leon-mc-rge-leon-62013-v1/nvidia
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-leon-mc-rge-leon-62013-v1/nvidia/config.json
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-leon-mc-rge-leon-62013-v1/nvidia/special_tokens_map.json
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-leon-mc-rge-leon-62013-v1/nvidia/tokenizer_config.json
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-leon-mc-rge-leon-62013-v1/nvidia/tokenizer.json
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-leon-mc-rge-leon-62013-v1/nvidia/flywheel_model.1.safetensors
chaiml-leon-mc-rge-leon-62013-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-leon-mc-rge-leon-62013-v1/nvidia/flywheel_model.0.safetensors
Job chaiml-leon-mc-rge-leon-62013-v1-mkmlizer completed after 268.3s with status: succeeded
Stopping job with name chaiml-leon-mc-rge-leon-62013-v1-mkmlizer
Pipeline stage MKMLizer completed in 269.09s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-leon-mc-rge-leon-62013-v1
Waiting for inference service chaiml-leon-mc-rge-leon-62013-v1 to be ready
HTTP Request: %s %s "%s %d %s"
Inference service chaiml-leon-mc-rge-leon-62013-v1 ready after 160.71175813674927s
Pipeline stage MKMLDeployer completed in 161.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.625370979309082s
Received healthy response to inference request in 2.553645372390747s
Received healthy response to inference request in 2.459831953048706s
Received healthy response to inference request in 2.880753993988037s
Received healthy response to inference request in 2.3265018463134766s
5 requests
0 failed requests
5th percentile: 2.3531678676605225
10th percentile: 2.3798338890075685
20th percentile: 2.43316593170166
30th percentile: 2.4785946369171143
40th percentile: 2.5161200046539305
50th percentile: 2.553645372390747
60th percentile: 2.582335615158081
70th percentile: 2.611025857925415
80th percentile: 2.6764475822448732
90th percentile: 2.778600788116455
95th percentile: 2.829677391052246
99th percentile: 2.870538673400879
mean time: 2.5692208290100096
Pipeline stage StressChecker completed in 14.38s
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 0.99s
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 0.62s
Shutdown handler de-registered
chaiml-leon-mc-rge-leon_62013_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 2584.79s
Shutdown handler de-registered
chaiml-leon-mc-rge-leon_62013_v1 status is now inactive due to auto deactivation removed underperforming models