allura-org-qwen2-5-32b-rp-ink

developer_uid: NischayDnk

submission_id: allura-org-qwen2-5-32b-rp-ink_v1

model_name: allura-org-qwen2-5-32b-rp-ink_v1

model_group: allura-org/Qwen2.5-32b-R

status: inactive

timestamp: 2025-04-03T23:12:23+00:00

num_battles: 11057

num_wins: 4049

celo_rating: 1190.02

family_friendly_score: 0.6452

family_friendly_standard_error: 0.006766342586656398

submission_type: basic

model_repo: allura-org/Qwen2.5-32b-RP-Ink

model_architecture: Qwen2ForCausalLM

model_num_parameters: 32763417600.0

best_of: 1

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.30276475625067983, 'latency_mean': 3.3028356432914734, 'latency_p50': 3.28437340259552, 'latency_p90': 3.7014418125152586}, {'batch_size': 3, 'throughput': 0.7070035313986142, 'latency_mean': 4.232899338006973, 'latency_p50': 4.2604451179504395, 'latency_p90': 4.636995530128479}, {'batch_size': 5, 'throughput': 1.0486292533258437, 'latency_mean': 4.746588158607483, 'latency_p50': 4.722625494003296, 'latency_p90': 5.36917655467987}, {'batch_size': 6, 'throughput': 1.172257176763416, 'latency_mean': 5.0783525550365445, 'latency_p50': 5.086583375930786, 'latency_p90': 5.662692046165466}, {'batch_size': 10, 'throughput': 1.5863909263941731, 'latency_mean': 6.255246841907502, 'latency_p50': 6.216525197029114, 'latency_p90': 6.980554509162903}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: allura-org-qwen2-5-32b-rp-ink_v1

is_internal_developer: True

language_model: allura-org/Qwen2.5-32b-RP-Ink

model_size: 33B

ranking_group: single

throughput_3p7s: 0.5

us_pacific_date: 2025-04-03

win_ratio: 0.3661933616713394

generation_params: {'temperature': 0.7, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n:', '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-qwen2-5-32b-rp-ink-v1-mkmlizer
Waiting for job on allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer to finish
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║     _____            __           __                                ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║       /___/                                                         ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║                                                                     ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║  https://mk1.ai                                                     ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║                                                                     ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║  belonging to:                                                      ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║                                                                     ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║  Chai Research Corp.                                                ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ║                                                                     ║
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-slerpv6-merge-sl_91568_v1: HTTPConnectionPool(host='chaiml-slerpv6-merge-sl-91568-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x70eef078a850>, 'Connection to chaiml-slerpv6-merge-sl-91568-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v5: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: Downloaded to shared memory in 125.217s
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfnxk7ik7, device:0
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission qwen-qwq-32b_v1: HTTPConnectionPool(host='qwen-qwq-32b-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission qwen-qwq-32b_v1: HTTPConnectionPool(host='qwen-qwq-32b-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: quantized model in 64.184s
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: Processed model allura-org/Qwen2.5-32b-RP-Ink in 189.402s
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: creating bucket guanaco-mkml-models
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1/added_tokens.json
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1/config.json
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1/special_tokens_map.json
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1/tokenizer_config.json
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1/merges.txt
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1/vocab.json
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1/tokenizer.json
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1/flywheel_model.2.safetensors
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1/flywheel_model.0.safetensors
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/allura-org-qwen2-5-32b-rp-ink-v1/flywheel_model.1.safetensors
allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer: 
Loading 0:   0%|          | 0/771 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/771 [00:00<00:19, 38.75it/s]
Loading 0:   2%|▏         | 16/771 [00:00<00:10, 68.66it/s]
Loading 0:   4%|▎         | 27/771 [00:00<00:09, 80.82it/s]
Loading 0:   5%|▍         | 36/771 [00:00<00:13, 54.14it/s]
Loading 0:   6%|▌         | 43/771 [00:00<00:14, 49.43it/s]
Loading 0:   7%|▋         | 52/771 [00:00<00:12, 58.27it/s]
Loading 0:   8%|▊         | 63/771 [00:00<00:10, 70.31it/s]
Loading 0:   9%|▉         | 71/771 [00:01<00:09, 72.39it/s]
Loading 0:  11%|█         | 84/771 [00:01<00:10, 64.98it/s]
Loading 0:  12%|█▏        | 94/771 [00:01<00:09, 70.51it/s]
Loading 0:  13%|█▎        | 102/771 [00:01<00:10, 61.09it/s]
Loading 0:  14%|█▍        | 110/771 [00:01<00:10, 64.62it/s]
Loading 0:  16%|█▌        | 121/771 [00:01<00:08, 74.09it/s]
Loading 0:  17%|█▋        | 129/771 [00:01<00:08, 74.88it/s]
Loading 0:  18%|█▊        | 137/771 [00:02<00:14, 44.35it/s]
Loading 0:  19%|█▉        | 148/771 [00:02<00:11, 55.61it/s]
Loading 0:  21%|██        | 159/771 [00:02<00:09, 65.83it/s]
Loading 0:  22%|██▏       | 168/771 [00:02<00:08, 70.30it/s]
Loading 0:  23%|██▎       | 180/771 [00:02<00:10, 57.80it/s]
Loading 0:  24%|██▍       | 188/771 [00:03<00:10, 54.24it/s]
Loading 0:  25%|██▌       | 196/771 [00:03<00:09, 59.15it/s]
Loading 0:  27%|██▋       | 207/771 [00:03<00:08, 69.09it/s]
Loading 0:  28%|██▊       | 215/771 [00:03<00:07, 70.90it/s]
Loading 0:  30%|██▉       | 228/771 [00:03<00:08, 60.57it/s]
Loading 0:  30%|███       | 235/771 [00:03<00:09, 54.58it/s]
Loading 0:  32%|███▏      | 244/771 [00:03<00:08, 61.59it/s]
Loading 0:  33%|███▎      | 255/771 [00:04<00:07, 71.79it/s]
Loading 0:  34%|███▍      | 264/771 [00:04<00:06, 75.74it/s]
Loading 0:  36%|███▌      | 276/771 [00:04<00:08, 61.29it/s]
Loading 0:  37%|███▋      | 284/771 [00:04<00:08, 56.75it/s]
Loading 0:  38%|███▊      | 292/771 [00:04<00:07, 61.30it/s]
Loading 0:  39%|███▉      | 303/771 [00:19<03:38,  2.14it/s]
Loading 0:  40%|████      | 311/771 [00:19<02:40,  2.87it/s]
Loading 0:  42%|████▏     | 324/771 [00:19<01:42,  4.38it/s]
Loading 0:  43%|████▎     | 330/771 [00:20<01:23,  5.27it/s]
Loading 0:  44%|████▍     | 341/771 [00:20<00:55,  7.74it/s]
Loading 0:  46%|████▌     | 352/771 [00:20<00:37, 11.13it/s]
Loading 0:  47%|████▋     | 363/771 [00:20<00:26, 15.60it/s]
Loading 0:  48%|████▊     | 372/771 [00:20<00:21, 18.64it/s]
Loading 0:  49%|████▉     | 379/771 [00:20<00:18, 21.33it/s]
Loading 0:  50%|█████     | 388/771 [00:20<00:13, 27.58it/s]
Loading 0:  52%|█████▏    | 399/771 [00:21<00:10, 36.85it/s]
Loading 0:  53%|█████▎    | 407/771 [00:21<00:08, 42.73it/s]
Loading 0:  54%|█████▍    | 420/771 [00:21<00:07, 44.97it/s]
Loading 0:  55%|█████▌    | 427/771 [00:21<00:07, 43.89it/s]
Loading 0:  57%|█████▋    | 436/771 [00:21<00:06, 51.41it/s]
Loading 0:  58%|█████▊    | 447/771 [00:21<00:05, 62.03it/s]
Loading 0:  59%|█████▉    | 455/771 [00:21<00:04, 65.24it/s]
Loading 0:  61%|██████    | 468/771 [00:22<00:05, 55.46it/s]
Loading 0:  62%|██████▏   | 475/771 [00:22<00:05, 50.93it/s]
Loading 0:  63%|██████▎   | 484/771 [00:22<00:04, 57.84it/s]
Loading 0:  64%|██████▍   | 495/771 [00:22<00:04, 67.73it/s]
Loading 0:  65%|██████▌   | 503/771 [00:22<00:03, 69.11it/s]
Loading 0:  67%|██████▋   | 516/771 [00:23<00:04, 57.88it/s]
Loading 0:  68%|██████▊   | 523/771 [00:23<00:04, 52.39it/s]
Loading 0:  69%|██████▉   | 532/771 [00:23<00:04, 59.35it/s]
Loading 0:  70%|███████   | 543/771 [00:23<00:03, 69.26it/s]
Loading 0:  71%|███████▏  | 551/771 [00:23<00:03, 71.30it/s]
Loading 0:  73%|███████▎  | 564/771 [00:23<00:03, 60.12it/s]
Loading 0:  74%|███████▍  | 571/771 [00:23<00:03, 54.58it/s]
Loading 0:  75%|███████▌  | 580/771 [00:24<00:03, 61.10it/s]
Loading 0:  77%|███████▋  | 591/771 [00:24<00:02, 71.55it/s]
Loading 0:  78%|███████▊  | 600/771 [00:24<00:02, 74.92it/s]
Loading 0:  79%|███████▉  | 612/771 [00:24<00:02, 61.62it/s]
Loading 0:  80%|████████  | 620/771 [00:24<00:02, 57.29it/s]
Loading 0:  81%|████████▏ | 627/771 [00:39<01:12,  1.98it/s]
Loading 0:  82%|████████▏ | 636/771 [00:39<00:47,  2.82it/s]
Loading 0:  84%|████████▎ | 644/771 [00:39<00:33,  3.84it/s]
Loading 0:  86%|████████▌ | 660/771 [00:39<00:17,  6.39it/s]
Loading 0:  86%|████████▋ | 666/771 [00:39<00:13,  7.54it/s]
Loading 0:  88%|████████▊ | 677/771 [00:40<00:08, 10.81it/s]
Loading 0:  89%|████████▉ | 688/771 [00:40<00:05, 15.23it/s]
Loading 0:  91%|█████████ | 699/771 [00:40<00:03, 20.92it/s]
Loading 0:  92%|█████████▏| 708/771 [00:40<00:02, 24.17it/s]
Loading 0:  93%|█████████▎| 716/771 [00:40<00:01, 27.54it/s]
Loading 0:  94%|█████████▍| 725/771 [00:40<00:01, 33.14it/s]
Loading 0:  96%|█████████▌| 737/771 [00:40<00:00, 42.50it/s]
Loading 0:  98%|█████████▊| 756/771 [00:48<00:02,  5.11it/s]
Loading 0:  99%|█████████▉| 762/771 [00:48<00:01,  5.93it/s]
                                                            
Job allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer completed after 226.35s with status: succeeded
Stopping job with name allura-org-qwen2-5-32b-rp-ink-v1-mkmlizer
Pipeline stage MKMLizer completed in 226.77s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service allura-org-qwen2-5-32b-rp-ink-v1
Waiting for inference service allura-org-qwen2-5-32b-rp-ink-v1 to be ready
Failed to get response for submission chaiml-sft-gemma2-28b-v_83370_v5: HTTPConnectionPool(host='chaiml-sft-gemma2-28b-v-83370-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service allura-org-qwen2-5-32b-rp-ink-v1 ready after 120.39547920227051s
Pipeline stage MKMLDeployer completed in 120.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0543887615203857s
Received healthy response to inference request in 1.1346282958984375s
Received healthy response to inference request in 1.7327384948730469s
Received healthy response to inference request in 1.2127008438110352s
Received healthy response to inference request in 1.0638854503631592s
5 requests
0 failed requests
5th percentile: 1.078034019470215
10th percentile: 1.0921825885772705
20th percentile: 1.1204797267913817
30th percentile: 1.150242805480957
40th percentile: 1.181471824645996
50th percentile: 1.2127008438110352
60th percentile: 1.4207159042358397
70th percentile: 1.6287309646606445
80th percentile: 1.997068548202515
90th percentile: 2.5257286548614504
95th percentile: 2.7900587081909176
99th percentile: 3.001522750854492
mean time: 1.6396683692932128
Pipeline stage StressChecker completed in 9.48s
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 0.65s
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 0.64s
Shutdown handler de-registered
allura-org-qwen2-5-32b-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3977.61s
Shutdown handler de-registered
allura-org-qwen2-5-32b-rp-ink_v1 status is now inactive due to auto deactivation removed underperforming models

ChatRequest

Bot Name

Generation Params

Prompt Formatter

ChatMessage 1

Sender

Message

User Message