developer_uid: azuruce
submission_id: allura-org-mn-12b-rp-ink_v1
model_name: allura-org-mn-12b-rp-ink_v1
model_group: allura-org/MN-12b-RP-Ink
status: torndown
timestamp: 2025-01-09T23:50:22+00:00
num_battles: 7295
num_wins: 3500
celo_rating: 1227.95
family_friendly_score: 0.5886
family_friendly_standard_error: 0.006959167191553886
submission_type: basic
model_repo: allura-org/MN-12b-RP-Ink
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6361536582733291, 'latency_mean': 1.571886271238327, 'latency_p50': 1.5764737129211426, 'latency_p90': 1.7254469871520997}, {'batch_size': 3, 'throughput': 1.2677942152415398, 'latency_mean': 2.3608884918689728, 'latency_p50': 2.363209843635559, 'latency_p90': 2.5924856185913088}, {'batch_size': 5, 'throughput': 1.6028746593127898, 'latency_mean': 3.0969281685352326, 'latency_p50': 3.1048656702041626, 'latency_p90': 3.4872198581695555}, {'batch_size': 6, 'throughput': 1.72695852063529, 'latency_mean': 3.4504436802864076, 'latency_p50': 3.442907929420471, 'latency_p90': 3.893263030052185}, {'batch_size': 8, 'throughput': 1.883422965277768, 'latency_mean': 4.218110523223877, 'latency_p50': 4.240331053733826, 'latency_p90': 4.717177605628967}, {'batch_size': 10, 'throughput': 1.9698797117487719, 'latency_mean': 5.0528850710392, 'latency_p50': 5.063867568969727, 'latency_p90': 5.750736832618713}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: allura-org-mn-12b-rp-ink_v1
ineligible_reason: num_battles<10000
is_internal_developer: False
language_model: allura-org/MN-12b-RP-Ink
model_size: 13B
ranking_group: single
throughput_3p7s: 1.8
us_pacific_date: 2025-01-09
win_ratio: 0.47978067169294036
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.001, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['####', '<|eot_id|>', 'You:', 'User:', 'Bot:', '<|im_end|>', 'Me:', '\n', '</s>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
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 allura-org-mn-12b-rp-ink-v1-mkmlizer
Waiting for job on allura-org-mn-12b-rp-ink-v1-mkmlizer to finish
allura-org-mn-12b-rp-ink-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ _____ __ __ ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ /___/ ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ Version: 0.11.12 ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ https://mk1.ai ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ The license key for the current software has been verified as ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ belonging to: ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ Chai Research Corp. ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ║ ║
allura-org-mn-12b-rp-ink-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
allura-org-mn-12b-rp-ink-v1-mkmlizer: Downloaded to shared memory in 49.635s
allura-org-mn-12b-rp-ink-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphmbh4tin, device:0
allura-org-mn-12b-rp-ink-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
allura-org-mn-12b-rp-ink-v1-mkmlizer: quantized model in 36.128s
allura-org-mn-12b-rp-ink-v1-mkmlizer: Processed model allura-org/MN-12b-RP-Ink in 85.763s
allura-org-mn-12b-rp-ink-v1-mkmlizer: creating bucket guanaco-mkml-models
allura-org-mn-12b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/allura-org-mn-12b-rp-ink-v1/special_tokens_map.json
allura-org-mn-12b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/allura-org-mn-12b-rp-ink-v1/tokenizer_config.json
allura-org-mn-12b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/allura-org-mn-12b-rp-ink-v1/tokenizer.json
allura-org-mn-12b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/allura-org-mn-12b-rp-ink-v1/flywheel_model.0.safetensors
allura-org-mn-12b-rp-ink-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:11, 31.72it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 53.97it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:06, 51.11it/s] Loading 0: 7%|▋ | 25/363 [00:00<00:06, 52.47it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 54.78it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 52.30it/s] Loading 0: 12%|█▏ | 43/363 [00:00<00:06, 53.00it/s] Loading 0: 13%|█▎ | 49/363 [00:00<00:05, 55.00it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:05, 52.34it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:07, 38.44it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:07, 38.82it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:06, 43.28it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 43.58it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 44.26it/s] Loading 0: 25%|██▍ | 90/363 [00:01<00:05, 49.67it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 47.45it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:05, 44.35it/s] Loading 0: 29%|██▉ | 106/363 [00:02<00:05, 45.51it/s] Loading 0: 31%|███ | 113/363 [00:02<00:05, 44.78it/s] Loading 0: 33%|███▎ | 118/363 [00:02<00:05, 42.76it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:04, 49.94it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:04, 47.98it/s] Loading 0: 38%|███▊ | 137/363 [00:02<00:04, 46.01it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 35.00it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.62it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 34.15it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 39.66it/s] Loading 0: 44%|████▍ | 161/363 [00:03<00:04, 41.30it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 43.02it/s] Loading 0: 47%|████▋ | 172/363 [00:03<00:04, 43.27it/s] Loading 0: 49%|████▉ | 177/363 [00:03<00:04, 42.63it/s] Loading 0: 51%|█████ | 184/363 [00:04<00:03, 47.38it/s] Loading 0: 52%|█████▏ | 190/363 [00:04<00:03, 46.08it/s] Loading 0: 54%|█████▎ | 195/363 [00:04<00:03, 44.26it/s] Loading 0: 55%|█████▌ | 201/363 [00:04<00:03, 47.94it/s] Loading 0: 57%|█████▋ | 206/363 [00:04<00:03, 45.20it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 45.60it/s] Loading 0: 60%|█████▉ | 217/363 [00:04<00:03, 44.92it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:03, 35.17it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:03, 35.37it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:03, 34.60it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 39.69it/s] Loading 0: 67%|██████▋ | 242/363 [00:05<00:03, 39.96it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 40.72it/s] Loading 0: 70%|██████▉ | 253/363 [00:05<00:02, 40.21it/s] Loading 0: 71%|███████ | 258/363 [00:05<00:02, 38.70it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 42.75it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 42.16it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 41.97it/s] Loading 0: 77%|███████▋ | 279/363 [00:06<00:02, 41.99it/s] Loading 0: 78%|███████▊ | 284/363 [00:06<00:02, 35.74it/s] Loading 0: 80%|████████ | 291/363 [00:06<00:01, 43.27it/s] Loading 0: 82%|████████▏ | 296/363 [00:06<00:01, 43.46it/s] Loading 0: 83%|████████▎ | 301/363 [00:06<00:01, 44.60it/s] Loading 0: 84%|████████▍ | 306/363 [00:13<00:23, 2.39it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:17, 3.09it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:12, 4.07it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:07, 6.09it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 8.61it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 11.17it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.00it/s] Loading 0: 95%|█████████▍| 344/363 [00:14<00:00, 19.78it/s] Loading 0: 96%|█████████▌| 349/363 [00:14<00:00, 23.26it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 30.12it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 33.62it/s]
Job allura-org-mn-12b-rp-ink-v1-mkmlizer completed after 104.86s with status: succeeded
Stopping job with name allura-org-mn-12b-rp-ink-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.39s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service allura-org-mn-12b-rp-ink-v1
Waiting for inference service allura-org-mn-12b-rp-ink-v1 to be ready
Inference service allura-org-mn-12b-rp-ink-v1 ready after 371.95463037490845s
Pipeline stage MKMLDeployer completed in 372.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8322162628173828s
Received healthy response to inference request in 0.9993550777435303s
Received healthy response to inference request in 0.9486186504364014s
Received healthy response to inference request in 1.602675437927246s
Received healthy response to inference request in 1.326765775680542s
5 requests
0 failed requests
5th percentile: 0.9587659358978271
10th percentile: 0.968913221359253
20th percentile: 0.9892077922821045
30th percentile: 1.0648372173309326
40th percentile: 1.1958014965057373
50th percentile: 1.326765775680542
60th percentile: 1.4371296405792235
70th percentile: 1.5474935054779053
80th percentile: 1.6485836029052734
90th percentile: 1.7403999328613282
95th percentile: 1.7863080978393555
99th percentile: 1.8230346298217774
mean time: 1.3419262409210204
Pipeline stage StressChecker completed in 8.12s
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 0.78s
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 0.69s
Shutdown handler de-registered
allura-org-mn-12b-rp-ink_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2477.83s
Shutdown handler de-registered
allura-org-mn-12b-rp-ink_v1 status is now inactive due to auto deactivation removed underperforming models
allura-org-mn-12b-rp-ink_v1 status is now torndown due to DeploymentManager action