junhua024-chai-16-full-_96988

developer_uid: junhua024

submission_id: junhua024-chai-16-full-_96988_v1

model_name: junhua024-chai-16-full-_96988_v1

model_group: junhua024/chai_16_full_q

status: torndown

timestamp: 2025-07-20T08:33:30+00:00

num_battles: 5912

num_wins: 2902

celo_rating: 1281.78

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: junhua024/chai_16_full_qkv106_o106_ffn106_1925

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6023417060919136, 'latency_mean': 1.660083214044571, 'latency_p50': 1.663199543952942, 'latency_p90': 1.8217868328094482}, {'batch_size': 3, 'throughput': 1.100228715305183, 'latency_mean': 2.7211505448818207, 'latency_p50': 2.729223847389221, 'latency_p90': 2.9894614458084106}, {'batch_size': 5, 'throughput': 1.3076968521143477, 'latency_mean': 3.800721608400345, 'latency_p50': 3.8263511657714844, 'latency_p90': 4.131085014343261}, {'batch_size': 6, 'throughput': 1.3897407870997507, 'latency_mean': 4.289584212303161, 'latency_p50': 4.2868287563323975, 'latency_p90': 4.834716248512268}, {'batch_size': 8, 'throughput': 1.4489159081641612, 'latency_mean': 5.4897017776966095, 'latency_p50': 5.51908802986145, 'latency_p90': 6.1586366415023805}, {'batch_size': 10, 'throughput': 1.4699129583196315, 'latency_mean': 6.74055990934372, 'latency_p50': 6.730624437332153, 'latency_p90': 7.626853704452515}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-16-full-_96988_v1

is_internal_developer: False

language_model: junhua024/chai_16_full_qkv106_o106_ffn106_1925

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-07-20

win_ratio: 0.4908660351826793

generation_params: {'temperature': 1.0, 'top_p': 0.88, 'min_p': 0.0, 'top_k': 10, '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 junhua024-chai-16-full-96988-v1-mkmlizer
Waiting for job on junhua024-chai-16-full-96988-v1-mkmlizer to finish
junhua024-chai-16-full-96988-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-96988-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-96988-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-96988-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-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`
junhua024-chai-16-full-96988-v1-mkmlizer: Downloaded to shared memory in 121.993s
junhua024-chai-16-full-96988-v1-mkmlizer: Checking if junhua024/chai_16_full_qkv106_o106_ffn106_1925 already exists in ChaiML
junhua024-chai-16-full-96988-v1-mkmlizer: Creating repo ChaiML/chai_16_full_qkv106_o106_ffn106_1925 and uploading /tmp/tmp8nitq_2j to it
junhua024-chai-16-full-96988-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:01<00:47,  1.92s/it]
  8%|▊         | 2/26 [00:03<00:37,  1.56s/it]
 12%|█▏        | 3/26 [00:05<00:43,  1.89s/it]
 15%|█▌        | 4/26 [00:06<00:37,  1.69s/it]
 19%|█▉        | 5/26 [00:08<00:33,  1.58s/it]
 23%|██▎       | 6/26 [00:09<00:29,  1.49s/it]
 27%|██▋       | 7/26 [00:11<00:29,  1.58s/it]
 31%|███       | 8/26 [00:12<00:27,  1.50s/it]
 35%|███▍      | 9/26 [00:14<00:24,  1.45s/it]
 38%|███▊      | 10/26 [00:15<00:22,  1.41s/it]
 42%|████▏     | 11/26 [00:16<00:21,  1.41s/it]
 46%|████▌     | 12/26 [00:18<00:20,  1.45s/it]
 50%|█████     | 13/26 [00:19<00:18,  1.45s/it]
 54%|█████▍    | 14/26 [00:21<00:17,  1.50s/it]
 58%|█████▊    | 15/26 [00:22<00:16,  1.47s/it]
 62%|██████▏   | 16/26 [00:24<00:14,  1.44s/it]
 65%|██████▌   | 17/26 [00:27<00:19,  2.16s/it]
 69%|██████▉   | 18/26 [00:30<00:18,  2.36s/it]
 73%|███████▎  | 19/26 [00:32<00:15,  2.18s/it]
 77%|███████▋  | 20/26 [00:33<00:11,  1.91s/it]
 81%|████████  | 21/26 [00:35<00:09,  1.83s/it]
 85%|████████▍ | 22/26 [00:36<00:06,  1.70s/it]
 88%|████████▊ | 23/26 [00:38<00:04,  1.59s/it]
 92%|█████████▏| 24/26 [00:41<00:04,  2.15s/it]
 96%|█████████▌| 25/26 [00:43<00:01,  1.91s/it]
100%|██████████| 26/26 [00:44<00:00,  1.68s/it]
100%|██████████| 26/26 [00:44<00:00,  1.70s/it]
junhua024-chai-16-full-96988-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8nitq_2j, device:0
junhua024-chai-16-full-96988-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-96988-v1-mkmlizer: quantized model in 31.177s
junhua024-chai-16-full-96988-v1-mkmlizer: Processed model junhua024/chai_16_full_qkv106_o106_ffn106_1925 in 226.628s
junhua024-chai-16-full-96988-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-96988-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-96988-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v1/nvidia
junhua024-chai-16-full-96988-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v1/nvidia/config.json
junhua024-chai-16-full-96988-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v1/nvidia/special_tokens_map.json
junhua024-chai-16-full-96988-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v1/nvidia/tokenizer_config.json
junhua024-chai-16-full-96988-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v1/nvidia/tokenizer.json
Job junhua024-chai-16-full-96988-v1-mkmlizer completed after 255.19s with status: succeeded
Stopping job with name junhua024-chai-16-full-96988-v1-mkmlizer
Pipeline stage MKMLizer completed in 255.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-16-full-96988-v1
Waiting for inference service junhua024-chai-16-full-96988-v1 to be ready
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-96988-v1 ready after 332.80153155326843s
Pipeline stage MKMLDeployer completed in 333.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3763864040374756s
Received healthy response to inference request in 1.6338376998901367s
Received healthy response to inference request in 1.9672162532806396s
Received healthy response to inference request in 1.7252492904663086s
Received healthy response to inference request in 1.6570994853973389s
5 requests
0 failed requests
5th percentile: 1.6384900569915772
10th percentile: 1.6431424140930175
20th percentile: 1.6524471282958983
30th percentile: 1.6707294464111329
40th percentile: 1.6979893684387206
50th percentile: 1.7252492904663086
60th percentile: 1.822036075592041
70th percentile: 1.9188228607177733
80th percentile: 2.049050283432007
90th percentile: 2.2127183437347413
95th percentile: 2.294552373886108
99th percentile: 2.3600195980072023
mean time: 1.87195782661438
Pipeline stage StressChecker completed in 10.99s
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 0.75s
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 0.75s
Shutdown handler de-registered
junhua024-chai-16-full-_96988_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
junhua024-chai-16-full-_96988_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_96988_v1 status is now torndown due to DeploymentManager action