developer_uid: huohuo12
submission_id: yamatazen-ayla-light-12b-v2_v7
model_name: yamatazen-ayla-light-12b-v2_v2
model_group: yamatazen/Ayla-Light-12B
status: torndown
timestamp: 2025-02-26T09:37:38+00:00
num_battles: 6068
num_wins: 2958
celo_rating: 1258.51
family_friendly_score: 0.5684
family_friendly_standard_error: 0.007004590494811242
submission_type: basic
model_repo: yamatazen/Ayla-Light-12B-v2
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.5982667394797042, 'latency_mean': 1.6714286494255066, 'latency_p50': 1.6823556423187256, 'latency_p90': 1.83700430393219}, {'batch_size': 3, 'throughput': 1.097215950660106, 'latency_mean': 2.7247413671016694, 'latency_p50': 2.6945828199386597, 'latency_p90': 3.0269489526748656}, {'batch_size': 5, 'throughput': 1.324167096872707, 'latency_mean': 3.764209772348404, 'latency_p50': 3.778182029724121, 'latency_p90': 4.117162609100342}, {'batch_size': 6, 'throughput': 1.3826229044832163, 'latency_mean': 4.310098518133163, 'latency_p50': 4.341346621513367, 'latency_p90': 4.858139967918396}, {'batch_size': 8, 'throughput': 1.4606985903188965, 'latency_mean': 5.447049263715744, 'latency_p50': 5.443707704544067, 'latency_p90': 6.090493273735047}, {'batch_size': 10, 'throughput': 1.4839422506749824, 'latency_mean': 6.688594106435776, 'latency_p50': 6.7720218896865845, 'latency_p90': 7.606633162498474}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: yamatazen-ayla-light-12b-v2_v2
is_internal_developer: False
language_model: yamatazen/Ayla-Light-12B-v2
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-02-26
win_ratio: 0.487475280158207
generation_params: {'temperature': 0.75, 'top_p': 0.85, 'min_p': 0.25, 'top_k': 45, 'presence_penalty': 0.2, 'frequency_penalty': 0.5, 'stopping_words': ['\n'], '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 yamatazen-ayla-light-12b-v2-v7-mkmlizer
Waiting for job on yamatazen-ayla-light-12b-v2-v7-mkmlizer to finish
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ _____ __ __ ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ /___/ ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ Version: 0.12.8 ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ https://mk1.ai ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ The license key for the current software has been verified as ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ belonging to: ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ Chai Research Corp. ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ║ ║
yamatazen-ayla-light-12b-v2-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
yamatazen-ayla-light-12b-v2-v7-mkmlizer: Downloaded to shared memory in 32.371s
yamatazen-ayla-light-12b-v2-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdwkn_17b, device:0
yamatazen-ayla-light-12b-v2-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
yamatazen-ayla-light-12b-v2-v7-mkmlizer: quantized model in 36.115s
yamatazen-ayla-light-12b-v2-v7-mkmlizer: Processed model yamatazen/Ayla-Light-12B-v2 in 68.492s
yamatazen-ayla-light-12b-v2-v7-mkmlizer: creating bucket guanaco-mkml-models
yamatazen-ayla-light-12b-v2-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
yamatazen-ayla-light-12b-v2-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v7
yamatazen-ayla-light-12b-v2-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v7/config.json
yamatazen-ayla-light-12b-v2-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v7/special_tokens_map.json
yamatazen-ayla-light-12b-v2-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v7/tokenizer_config.json
yamatazen-ayla-light-12b-v2-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v7/tokenizer.json
yamatazen-ayla-light-12b-v2-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/yamatazen-ayla-light-12b-v2-v7/flywheel_model.0.safetensors
yamatazen-ayla-light-12b-v2-v7-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:06<18:22, 3.05s/it] Loading 0: 2%|▏ | 6/363 [00:06<04:53, 1.22it/s] Loading 0: 4%|▎ | 13/363 [00:06<01:44, 3.35it/s] Loading 0: 5%|▌ | 19/363 [00:06<00:59, 5.75it/s] Loading 0: 7%|▋ | 24/363 [00:06<00:42, 8.01it/s] Loading 0: 9%|▉ | 32/363 [00:06<00:25, 13.19it/s] Loading 0: 10%|█ | 38/363 [00:06<00:19, 16.87it/s] Loading 0: 12%|█▏ | 43/363 [00:07<00:18, 16.93it/s] Loading 0: 13%|█▎ | 49/363 [00:07<00:14, 21.64it/s] Loading 0: 15%|█▍ | 54/363 [00:07<00:12, 25.37it/s] Loading 0: 16%|█▋ | 59/363 [00:07<00:10, 29.45it/s] Loading 0: 18%|█▊ | 65/363 [00:07<00:09, 32.67it/s] Loading 0: 19%|█▉ | 70/363 [00:07<00:08, 35.16it/s] Loading 0: 21%|██ | 77/363 [00:07<00:06, 41.60it/s] Loading 0: 23%|██▎ | 83/363 [00:08<00:06, 42.35it/s] Loading 0: 24%|██▍ | 88/363 [00:08<00:06, 43.15it/s] Loading 0: 26%|██▌ | 95/363 [00:08<00:05, 47.68it/s] Loading 0: 28%|██▊ | 101/363 [00:08<00:05, 45.78it/s] Loading 0: 29%|██▉ | 106/363 [00:08<00:05, 45.38it/s] Loading 0: 31%|███ | 113/363 [00:08<00:05, 49.59it/s] Loading 0: 33%|███▎ | 119/363 [00:08<00:05, 46.90it/s] Loading 0: 34%|███▍ | 124/363 [00:09<00:07, 33.12it/s] Loading 0: 36%|███▌ | 130/363 [00:09<00:06, 38.34it/s] Loading 0: 37%|███▋ | 135/363 [00:09<00:05, 39.51it/s] Loading 0: 39%|███▊ | 140/363 [00:09<00:05, 41.17it/s] Loading 0: 40%|████ | 146/363 [00:09<00:05, 41.05it/s] Loading 0: 42%|████▏ | 151/363 [00:09<00:05, 41.55it/s] Loading 0: 43%|████▎ | 157/363 [00:09<00:04, 44.70it/s] Loading 0: 45%|████▍ | 162/363 [00:09<00:04, 43.16it/s] Loading 0: 46%|████▌ | 167/363 [00:09<00:04, 43.53it/s] Loading 0: 48%|████▊ | 173/363 [00:10<00:04, 43.10it/s] Loading 0: 49%|████▉ | 178/363 [00:10<00:04, 41.94it/s] Loading 0: 51%|█████ | 184/363 [00:10<00:03, 45.65it/s] Loading 0: 52%|█████▏ | 189/363 [00:10<00:03, 44.68it/s] Loading 0: 53%|█████▎ | 194/363 [00:10<00:03, 44.76it/s] Loading 0: 55%|█████▌ | 200/363 [00:10<00:03, 43.21it/s] Loading 0: 56%|█████▋ | 205/363 [00:11<00:05, 30.93it/s] Loading 0: 58%|█████▊ | 211/363 [00:11<00:04, 34.78it/s] Loading 0: 59%|█████▉ | 215/363 [00:11<00:04, 33.86it/s] Loading 0: 61%|██████ | 220/363 [00:11<00:04, 35.42it/s] Loading 0: 62%|██████▏ | 224/363 [00:11<00:03, 35.40it/s] Loading 0: 63%|██████▎ | 230/363 [00:11<00:03, 39.48it/s] Loading 0: 65%|██████▍ | 235/363 [00:11<00:03, 41.20it/s] Loading 0: 66%|██████▌ | 240/363 [00:11<00:03, 32.84it/s] Loading 0: 68%|██████▊ | 247/363 [00:12<00:02, 40.35it/s] Loading 0: 69%|██████▉ | 252/363 [00:12<00:02, 41.29it/s] Loading 0: 71%|███████ | 257/363 [00:12<00:02, 42.60it/s] Loading 0: 72%|███████▏ | 262/363 [00:12<00:02, 44.28it/s] Loading 0: 74%|███████▎ | 267/363 [00:12<00:02, 37.57it/s] Loading 0: 75%|███████▌ | 274/363 [00:12<00:01, 44.91it/s] Loading 0: 77%|███████▋ | 279/363 [00:12<00:01, 45.34it/s] Loading 0: 78%|███████▊ | 284/363 [00:13<00:02, 33.70it/s] Loading 0: 79%|███████▉ | 288/363 [00:13<00:02, 34.69it/s] Loading 0: 81%|████████ | 293/363 [00:13<00:01, 37.02it/s] Loading 0: 82%|████████▏ | 299/363 [00:13<00:01, 37.64it/s] Loading 0: 84%|████████▎ | 304/363 [00:13<00:01, 38.60it/s] Loading 0: 86%|████████▌ | 311/363 [00:13<00:01, 44.51it/s] Loading 0: 87%|████████▋ | 317/363 [00:13<00:01, 44.30it/s] Loading 0: 89%|████████▊ | 322/363 [00:13<00:00, 42.35it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:00, 47.02it/s] Loading 0: 92%|█████████▏| 335/363 [00:14<00:00, 45.24it/s] Loading 0: 94%|█████████▎| 340/363 [00:14<00:00, 42.87it/s] Loading 0: 95%|█████████▌| 346/363 [00:14<00:00, 44.23it/s] Loading 0: 97%|█████████▋| 351/363 [00:14<00:00, 44.24it/s] Loading 0: 98%|█████████▊| 356/363 [00:14<00:00, 43.90it/s] Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 43.05it/s]
Job yamatazen-ayla-light-12b-v2-v7-mkmlizer completed after 93.65s with status: succeeded
Stopping job with name yamatazen-ayla-light-12b-v2-v7-mkmlizer
Pipeline stage MKMLizer completed in 94.11s
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 yamatazen-ayla-light-12b-v2-v7
Waiting for inference service yamatazen-ayla-light-12b-v2-v7 to be ready
Inference service yamatazen-ayla-light-12b-v2-v7 ready after 270.9313757419586s
Failed to get response for submission nischaydnk-exp16-mistra_31861_v2: HTTPConnectionPool(host='nischaydnk-exp16-mistra-31861-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Pipeline stage MKMLDeployer completed in 271.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.113781452178955s
Received healthy response to inference request in 0.978712797164917s
Received healthy response to inference request in 1.440722942352295s
Received healthy response to inference request in 1.4750382900238037s
Received healthy response to inference request in 1.7480533123016357s
5 requests
0 failed requests
5th percentile: 1.0711148262023926
10th percentile: 1.1635168552398683
20th percentile: 1.3483209133148193
30th percentile: 1.4475860118865966
40th percentile: 1.4613121509552003
50th percentile: 1.4750382900238037
60th percentile: 1.5842442989349366
70th percentile: 1.6934503078460692
80th percentile: 1.8211989402770996
90th percentile: 1.9674901962280273
95th percentile: 2.040635824203491
99th percentile: 2.0991523265838623
mean time: 1.5512617588043214
Pipeline stage StressChecker completed in 9.06s
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 0.68s
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 0.63s
Shutdown handler de-registered
yamatazen-ayla-light-12b-v2_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2587.67s
Shutdown handler de-registered
yamatazen-ayla-light-12b-v2_v7 status is now inactive due to auto deactivation removed underperforming models
yamatazen-ayla-light-12b-v2_v7 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1