djuna-q2-5-veltha-14b

developer_uid: huohuo12

submission_id: djuna-q2-5-veltha-14b_v1

model_name: djuna-q2-5-veltha-14b_v1

model_group: djuna/Q2.5-Veltha-14B

status: torndown

timestamp: 2025-02-20T07:31:50+00:00

num_battles: 6433

num_wins: 3130

celo_rating: 1231.77

family_friendly_score: 0.5973999999999999

family_friendly_standard_error: 0.006935607255316581

submission_type: basic

model_repo: djuna/Q2.5-Veltha-14B

model_architecture: Qwen2ForCausalLM

model_num_parameters: 14765603840.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.4764035400921192, 'latency_mean': 2.098966213464737, 'latency_p50': 2.1120193004608154, 'latency_p90': 2.312817335128784}, {'batch_size': 3, 'throughput': 0.8860818940176252, 'latency_mean': 3.3785961127281188, 'latency_p50': 3.387958288192749, 'latency_p90': 3.66538188457489}, {'batch_size': 5, 'throughput': 1.073366757711461, 'latency_mean': 4.6300554430484775, 'latency_p50': 4.594204306602478, 'latency_p90': 5.269899678230286}, {'batch_size': 6, 'throughput': 1.1442003034491712, 'latency_mean': 5.2128804695606235, 'latency_p50': 5.197041630744934, 'latency_p90': 5.890565872192383}, {'batch_size': 10, 'throughput': 1.2311303054437892, 'latency_mean': 8.057508236169815, 'latency_p50': 7.993263602256775, 'latency_p90': 9.158655595779418}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: djuna-q2-5-veltha-14b_v1

is_internal_developer: False

language_model: djuna/Q2.5-Veltha-14B

model_size: 15B

ranking_group: single

throughput_3p7s: 0.95

us_pacific_date: 2025-02-19

win_ratio: 0.48655370744598164

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'], '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 djuna-q2-5-veltha-14b-v1-mkmlizer
Waiting for job on djuna-q2-5-veltha-14b-v1-mkmlizer to finish
djuna-q2-5-veltha-14b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
djuna-q2-5-veltha-14b-v1-mkmlizer: ║     _____            __           __                                ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║       /___/                                                         ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║                                                                     ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║                                                                     ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║  belonging to:                                                      ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║                                                                     ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ║                                                                     ║
djuna-q2-5-veltha-14b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
djuna-q2-5-veltha-14b-v1-mkmlizer: Downloaded to shared memory in 56.042s
djuna-q2-5-veltha-14b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4h_6_f0d, device:0
djuna-q2-5-veltha-14b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
djuna-q2-5-veltha-14b-v1-mkmlizer: quantized model in 37.349s
djuna-q2-5-veltha-14b-v1-mkmlizer: Processed model djuna/Q2.5-Veltha-14B in 93.391s
djuna-q2-5-veltha-14b-v1-mkmlizer: creating bucket guanaco-mkml-models
djuna-q2-5-veltha-14b-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/djuna-q2-5-veltha-14b-v1/added_tokens.json
djuna-q2-5-veltha-14b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/djuna-q2-5-veltha-14b-v1/tokenizer_config.json
djuna-q2-5-veltha-14b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/djuna-q2-5-veltha-14b-v1/special_tokens_map.json
djuna-q2-5-veltha-14b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/djuna-q2-5-veltha-14b-v1/config.json
djuna-q2-5-veltha-14b-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/djuna-q2-5-veltha-14b-v1/merges.txt
djuna-q2-5-veltha-14b-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/djuna-q2-5-veltha-14b-v1/vocab.json
djuna-q2-5-veltha-14b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/djuna-q2-5-veltha-14b-v1/tokenizer.json
djuna-q2-5-veltha-14b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/djuna-q2-5-veltha-14b-v1/flywheel_model.1.safetensors
djuna-q2-5-veltha-14b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/djuna-q2-5-veltha-14b-v1/flywheel_model.0.safetensors
djuna-q2-5-veltha-14b-v1-mkmlizer: 
Loading 0:   0%|          | 0/579 [00:00<?, ?it/s]
Loading 0:   0%|          | 2/579 [00:07<34:20,  3.57s/it]
Loading 0:   3%|▎         | 16/579 [00:07<03:06,  3.01it/s]
Loading 0:   5%|▌         | 29/579 [00:07<01:25,  6.45it/s]
Loading 0:   7%|▋         | 41/579 [00:07<00:54,  9.79it/s]
Loading 0:   9%|▉         | 54/579 [00:07<00:34, 15.29it/s]
Loading 0:  12%|█▏        | 70/579 [00:07<00:21, 24.21it/s]
Loading 0:  15%|█▍        | 84/579 [00:08<00:14, 33.61it/s]
Loading 0:  17%|█▋        | 100/579 [00:08<00:10, 46.02it/s]
Loading 0:  20%|█▉        | 113/579 [00:08<00:08, 55.81it/s]
Loading 0:  22%|██▏       | 126/579 [00:08<00:06, 65.91it/s]
Loading 0:  25%|██▍       | 142/579 [00:08<00:05, 82.40it/s]
Loading 0:  27%|██▋       | 156/579 [00:08<00:06, 65.30it/s]
Loading 0:  30%|██▉       | 172/579 [00:08<00:05, 78.63it/s]
Loading 0:  32%|███▏      | 185/579 [00:09<00:04, 86.42it/s]
Loading 0:  34%|███▍      | 198/579 [00:09<00:04, 93.67it/s]
Loading 0:  37%|███▋      | 214/579 [00:09<00:03, 108.49it/s]
Loading 0:  39%|███▉      | 228/579 [00:09<00:03, 115.65it/s]
Loading 0:  42%|████▏     | 244/579 [00:09<00:02, 122.66it/s]
Loading 0:  45%|████▍     | 258/579 [00:09<00:04, 76.98it/s] 
Loading 0:  48%|████▊     | 276/579 [00:09<00:03, 95.02it/s]
Loading 0:  50%|█████     | 292/579 [00:10<00:02, 106.26it/s]
Loading 0:  53%|█████▎    | 306/579 [00:10<00:02, 107.12it/s]
Loading 0:  56%|█████▌    | 324/579 [00:10<00:02, 122.40it/s]
Loading 0:  59%|█████▊    | 340/579 [00:10<00:01, 128.51it/s]
Loading 0:  61%|██████▏   | 355/579 [00:10<00:01, 124.47it/s]
Loading 0:  64%|██████▎   | 369/579 [00:10<00:02, 84.29it/s] 
Loading 0:  66%|██████▋   | 384/579 [00:10<00:02, 95.80it/s]
Loading 0:  69%|██████▉   | 400/579 [00:10<00:01, 107.55it/s]
Loading 0:  71%|███████▏  | 413/579 [00:11<00:01, 110.34it/s]
Loading 0:  74%|███████▎  | 426/579 [00:11<00:01, 113.52it/s]
Loading 0:  77%|███████▋  | 444/579 [00:11<00:01, 129.19it/s]
Loading 0:  79%|███████▉  | 460/579 [00:11<00:00, 134.25it/s]
Loading 0:  82%|████████▏ | 475/579 [00:11<00:01, 82.73it/s] 
Loading 0:  84%|████████▍ | 487/579 [00:26<00:28,  3.18it/s]
Loading 0:  87%|████████▋ | 501/579 [00:26<00:17,  4.47it/s]
Loading 0:  89%|████████▉ | 514/579 [00:26<00:10,  6.13it/s]
Loading 0:  91%|█████████ | 527/579 [00:26<00:06,  8.43it/s]
Loading 0:  94%|█████████▍| 544/579 [00:26<00:02, 12.53it/s]
Loading 0:  96%|█████████▌| 557/579 [00:26<00:01, 16.59it/s]
Loading 0:  98%|█████████▊| 570/579 [00:27<00:00, 21.81it/s]
                                                            
Job djuna-q2-5-veltha-14b-v1-mkmlizer completed after 124.94s with status: succeeded
Stopping job with name djuna-q2-5-veltha-14b-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.42s
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 djuna-q2-5-veltha-14b-v1
Waiting for inference service djuna-q2-5-veltha-14b-v1 to be ready
Inference service djuna-q2-5-veltha-14b-v1 ready after 190.65141105651855s
Pipeline stage MKMLDeployer completed in 191.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6239054203033447s
Received healthy response to inference request in 1.9698755741119385s
Received healthy response to inference request in 2.1471598148345947s
Received healthy response to inference request in 1.9925358295440674s
Received healthy response to inference request in 2.0653903484344482s
5 requests
0 failed requests
5th percentile: 1.9744076251983642
10th percentile: 1.97893967628479
20th percentile: 1.9880037784576416
30th percentile: 2.0071067333221437
40th percentile: 2.036248540878296
50th percentile: 2.0653903484344482
60th percentile: 2.098098134994507
70th percentile: 2.1308059215545656
80th percentile: 2.242508935928345
90th percentile: 2.4332071781158446
95th percentile: 2.5285562992095945
99th percentile: 2.6048355960845946
mean time: 2.1597733974456785
Pipeline stage StressChecker completed in 12.26s
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 0.71s
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
djuna-q2-5-veltha-14b_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 2811.51s
Shutdown handler de-registered
djuna-q2-5-veltha-14b_v1 status is now inactive due to auto deactivation removed underperforming models
djuna-q2-5-veltha-14b_v1 status is now torndown due to DeploymentManager action