sao10k-l3-8b-lunaris-v1

developer_uid: Luna1040

submission_id: sao10k-l3-8b-lunaris-v1_v7

model_name: sao10k-l3-8b-lunaris-v1_v7

model_group: Sao10K/L3-8B-Lunaris-v1

status: torndown

timestamp: 2025-07-01T14:54:46+00:00

num_battles: 7802

num_wins: 3210

celo_rating: 1221.38

family_friendly_score: 0.5688

family_friendly_standard_error: 0.00700380696478708

submission_type: basic

model_repo: Sao10K/L3-8B-Lunaris-v1

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.8282442100062287, 'latency_mean': 1.2072219121456147, 'latency_p50': 1.2062561511993408, 'latency_p90': 1.3427223920822144}, {'batch_size': 4, 'throughput': 1.6820735211686142, 'latency_mean': 2.36962171792984, 'latency_p50': 2.368581175804138, 'latency_p90': 2.668352150917053}, {'batch_size': 5, 'throughput': 1.7808318004227786, 'latency_mean': 2.794539279937744, 'latency_p50': 2.799789786338806, 'latency_p90': 3.0942421197891234}, {'batch_size': 8, 'throughput': 1.9896449239071596, 'latency_mean': 3.9897891163825987, 'latency_p50': 3.9714726209640503, 'latency_p90': 4.4765788316726685}, {'batch_size': 10, 'throughput': 2.0213954112044985, 'latency_mean': 4.906901856660843, 'latency_p50': 4.894898891448975, 'latency_p90': 5.519790530204773}, {'batch_size': 12, 'throughput': 2.057221414630871, 'latency_mean': 5.769924006462097, 'latency_p50': 5.782451748847961, 'latency_p90': 6.4498426675796505}, {'batch_size': 15, 'throughput': 2.070707154236285, 'latency_mean': 7.146899886131287, 'latency_p50': 7.114645481109619, 'latency_p90': 8.10984935760498}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sao10k-l3-8b-lunaris-v1_v7

is_internal_developer: False

language_model: Sao10K/L3-8B-Lunaris-v1

model_size: 8B

ranking_group: single

throughput_3p7s: 1.97

us_pacific_date: 2025-07-01

win_ratio: 0.4114329659061779

generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 150, 'presence_penalty': 0.7, 'frequency_penalty': 0.7, 'stopping_words': ['[/INST]', '[INST]', '|im_end|', '<|eot_id|>', '<|start_header_id|>'], '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 sao10k-l3-8b-lunaris-v1-v7-mkmlizer
Waiting for job on sao10k-l3-8b-lunaris-v1-v7-mkmlizer to finish
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║                                                                     ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║                                                                     ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  Version: 0.29.3                                                    ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║                                                                     ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  belonging to:                                                      ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║                                                                     ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ║                                                                     ║
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-l3-8b-lunaris-v1-v7-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`
sao10k-l3-8b-lunaris-v1-v7-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`
sao10k-l3-8b-lunaris-v1-v7-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`
sao10k-l3-8b-lunaris-v1-v7-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`
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: Downloaded to shared memory in 52.378s
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: Checking if Sao10K/L3-8B-Lunaris-v1 already exists in ChaiML
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: Creating repo ChaiML/L3-8B-Lunaris-v1 and uploading /tmp/tmpilc1142a to it
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: 
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:04<00:13,  4.36s/it]
 50%|█████     | 2/4 [00:12<00:13,  6.56s/it]
 75%|███████▌  | 3/4 [00:16<00:05,  5.58s/it]
100%|██████████| 4/4 [00:19<00:00,  4.38s/it]
100%|██████████| 4/4 [00:19<00:00,  4.85s/it]
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpilc1142a, device:0
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: quantized model in 22.354s
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: Processed model Sao10K/L3-8B-Lunaris-v1 in 113.921s
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: creating bucket guanaco-mkml-models
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v7
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v7/config.json
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v7/special_tokens_map.json
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v7/tokenizer_config.json
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v7/tokenizer.json
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-l3-8b-lunaris-v1-v7/flywheel_model.0.safetensors
sao10k-l3-8b-lunaris-v1-v7-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/291 [00:04<11:56,  2.48s/it]
Loading 0:   2%|▏         | 6/291 [00:05<03:10,  1.49it/s]
Loading 0:   5%|▍         | 14/291 [00:05<01:02,  4.46it/s]
Loading 0:   7%|▋         | 20/291 [00:05<00:38,  7.11it/s]
Loading 0:   9%|▊         | 25/291 [00:05<00:26,  9.86it/s]
Loading 0:  11%|█         | 32/291 [00:05<00:17, 14.82it/s]
Loading 0:  13%|█▎        | 38/291 [00:05<00:13, 18.45it/s]
Loading 0:  15%|█▍        | 43/291 [00:05<00:11, 21.76it/s]
Loading 0:  17%|█▋        | 50/291 [00:06<00:08, 28.38it/s]
Loading 0:  19%|█▉        | 55/291 [00:06<00:07, 32.04it/s]
Loading 0:  21%|██        | 60/291 [00:06<00:10, 21.76it/s]
Loading 0:  23%|██▎       | 68/291 [00:06<00:07, 29.60it/s]
Loading 0:  25%|██▌       | 73/291 [00:06<00:06, 32.88it/s]
Loading 0:  27%|██▋       | 78/291 [00:06<00:06, 30.73it/s]
Loading 0:  30%|██▉       | 86/291 [00:07<00:05, 38.90it/s]
Loading 0:  32%|███▏      | 92/291 [00:07<00:05, 38.22it/s]
Loading 0:  33%|███▎      | 97/291 [00:07<00:04, 39.25it/s]
Loading 0:  36%|███▌      | 104/291 [00:07<00:04, 44.74it/s]
Loading 0:  38%|███▊      | 110/291 [00:07<00:04, 42.67it/s]
Loading 0:  40%|███▉      | 115/291 [00:07<00:04, 42.47it/s]
Loading 0:  42%|████▏     | 121/291 [00:07<00:03, 46.61it/s]
Loading 0:  43%|████▎     | 126/291 [00:07<00:03, 46.04it/s]
Loading 0:  45%|████▌     | 131/291 [00:08<00:03, 44.98it/s]
Loading 0:  47%|████▋     | 136/291 [00:08<00:03, 45.54it/s]
Loading 0:  48%|████▊     | 141/291 [00:08<00:03, 37.61it/s]
Loading 0:  51%|█████     | 149/291 [00:08<00:03, 46.29it/s]
Loading 0:  53%|█████▎    | 155/291 [00:08<00:03, 43.82it/s]
Loading 0:  55%|█████▍    | 160/291 [00:08<00:03, 42.85it/s]
Loading 0:  57%|█████▋    | 166/291 [00:09<00:04, 31.02it/s]
Loading 0:  58%|█████▊    | 170/291 [00:09<00:03, 32.25it/s]
Loading 0:  60%|██████    | 175/291 [00:09<00:03, 35.15it/s]
Loading 0:  62%|██████▏   | 179/291 [00:09<00:03, 36.10it/s]
Loading 0:  64%|██████▎   | 185/291 [00:09<00:02, 40.60it/s]
Loading 0:  66%|██████▌   | 191/291 [00:09<00:02, 39.44it/s]
Loading 0:  67%|██████▋   | 196/291 [00:09<00:02, 40.24it/s]
Loading 0:  69%|██████▉   | 202/291 [00:09<00:01, 45.04it/s]
Loading 0:  71%|███████   | 207/291 [00:09<00:01, 45.52it/s]
Loading 0:  73%|███████▎  | 212/291 [00:10<00:01, 45.86it/s]
Loading 0:  75%|███████▍  | 218/291 [00:10<00:01, 43.12it/s]
Loading 0:  77%|███████▋  | 223/291 [00:10<00:01, 42.65it/s]
Loading 0:  79%|███████▊  | 229/291 [00:10<00:01, 46.76it/s]
Loading 0:  80%|████████  | 234/291 [00:10<00:01, 46.73it/s]
Loading 0:  82%|████████▏ | 239/291 [00:10<00:01, 46.84it/s]
Loading 0:  84%|████████▍ | 245/291 [00:10<00:01, 42.74it/s]
Loading 0:  86%|████████▌ | 250/291 [00:10<00:00, 42.21it/s]
Loading 0:  88%|████████▊ | 257/291 [00:11<00:00, 47.32it/s]
Loading 0:  90%|█████████ | 263/291 [00:11<00:00, 44.43it/s]
Loading 0:  92%|█████████▏| 268/291 [00:11<00:00, 29.74it/s]
Loading 0:  94%|█████████▍| 274/291 [00:11<00:00, 34.58it/s]
Loading 0:  96%|█████████▌| 279/291 [00:11<00:00, 37.02it/s]
Loading 0:  98%|█████████▊| 284/291 [00:11<00:00, 39.30it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00, 38.76it/s]
                                                            
Job sao10k-l3-8b-lunaris-v1-v7-mkmlizer completed after 135.63s with status: succeeded
Stopping job with name sao10k-l3-8b-lunaris-v1-v7-mkmlizer
Pipeline stage MKMLizer completed in 136.11s
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 sao10k-l3-8b-lunaris-v1-v7
Waiting for inference service sao10k-l3-8b-lunaris-v1-v7 to be ready
Failed to get response for submission chaiml-mistralnemo-12b-_88791_v2: HTTPConnectionPool(host='chaiml-mistralnemo-12b-88791-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission auriaetherwiing-mn-12b-_82974_v3: HTTPConnectionPool(host='auriaetherwiing-mn-12b-82974-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission auriaetherwiing-mn-12b-_82974_v3: HTTPConnectionPool(host='auriaetherwiing-mn-12b-82974-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service sao10k-l3-8b-lunaris-v1-v7 ready after 210.83744764328003s
Pipeline stage MKMLDeployer completed in 211.71s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1023378372192383s
Received healthy response to inference request in 1.8960816860198975s
Received healthy response to inference request in 1.3858652114868164s
Received healthy response to inference request in 1.7230815887451172s
Received healthy response to inference request in 1.2303705215454102s
5 requests
0 failed requests
5th percentile: 1.2614694595336915
10th percentile: 1.2925683975219726
20th percentile: 1.354766273498535
30th percentile: 1.4533084869384765
40th percentile: 1.5881950378417968
50th percentile: 1.7230815887451172
60th percentile: 1.7922816276550293
70th percentile: 1.8614816665649414
80th percentile: 1.9373329162597657
90th percentile: 2.019835376739502
95th percentile: 2.0610866069793703
99th percentile: 2.094087591171265
mean time: 1.6675473690032958
Pipeline stage StressChecker completed in 9.85s
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 0.69s
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
sao10k-l3-8b-lunaris-v1_v7 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4558.43s
Shutdown handler de-registered
sao10k-l3-8b-lunaris-v1_v7 status is now inactive due to auto deactivation removed underperforming models
sao10k-l3-8b-lunaris-v1_v7 status is now torndown due to DeploymentManager action