developer_uid: junhua024
submission_id: junhua024-chai-16-full-_69709_v8
model_name: junhua024-chai-16-full-_69709_v8
model_group: junhua024/chai_16_full_1
status: torndown
timestamp: 2025-07-19T18:03:38+00:00
num_battles: 9922
num_wins: 4935
celo_rating: 1278.51
family_friendly_score: 0.5512
family_friendly_standard_error: 0.007033897354951947
submission_type: basic
model_repo: junhua024/chai_16_full_104_o_ffn_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': 0.58843857121746, 'latency_mean': 1.6992300939559937, 'latency_p50': 1.7039673328399658, 'latency_p90': 1.8769385814666748}, {'batch_size': 3, 'throughput': 1.0630151635142746, 'latency_mean': 2.8119120383262635, 'latency_p50': 2.806193232536316, 'latency_p90': 3.0724978923797606}, {'batch_size': 5, 'throughput': 1.2844968404540775, 'latency_mean': 3.8748665189743043, 'latency_p50': 3.859858751296997, 'latency_p90': 4.347107696533203}, {'batch_size': 6, 'throughput': 1.3420069481837142, 'latency_mean': 4.451938892602921, 'latency_p50': 4.470725059509277, 'latency_p90': 4.959380960464477}, {'batch_size': 8, 'throughput': 1.4023081408970126, 'latency_mean': 5.6703965985775, 'latency_p50': 5.666773676872253, 'latency_p90': 6.403416419029235}, {'batch_size': 10, 'throughput': 1.4351247313829154, 'latency_mean': 6.904197865724564, 'latency_p50': 6.959478259086609, 'latency_p90': 7.678750729560852}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-16-full-_69709_v8
is_internal_developer: False
language_model: junhua024/chai_16_full_104_o_ffn_1925
model_size: 13B
ranking_group: single
throughput_3p7s: 1.26
us_pacific_date: 2025-07-19
win_ratio: 0.49737956057246524
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-69709-v8-mkmlizer
Waiting for job on junhua024-chai-16-full-69709-v8-mkmlizer to finish
junhua024-chai-16-full-69709-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-69709-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-69709-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-69709-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-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-69709-v8-mkmlizer: Downloaded to shared memory in 79.128s
junhua024-chai-16-full-69709-v8-mkmlizer: Checking if junhua024/chai_16_full_104_o_ffn_1925 already exists in ChaiML
junhua024-chai-16-full-69709-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptg1uq25i, device:0
junhua024-chai-16-full-69709-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-69709-v8-mkmlizer: quantized model in 31.883s
junhua024-chai-16-full-69709-v8-mkmlizer: Processed model junhua024/chai_16_full_104_o_ffn_1925 in 111.097s
junhua024-chai-16-full-69709-v8-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-69709-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-69709-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-69709-v8/nvidia
junhua024-chai-16-full-69709-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-69709-v8/nvidia/config.json
junhua024-chai-16-full-69709-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-69709-v8/nvidia/special_tokens_map.json
junhua024-chai-16-full-69709-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-69709-v8/nvidia/tokenizer_config.json
junhua024-chai-16-full-69709-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-69709-v8/nvidia/tokenizer.json
junhua024-chai-16-full-69709-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-69709-v8/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-16-full-69709-v8-mkmlizer completed after 139.1s with status: succeeded
Stopping job with name junhua024-chai-16-full-69709-v8-mkmlizer
Pipeline stage MKMLizer completed in 139.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-16-full-69709-v8
Waiting for inference service junhua024-chai-16-full-69709-v8 to be ready
Inference service junhua024-chai-16-full-69709-v8 ready after 322.0176577568054s
Pipeline stage MKMLDeployer completed in 322.74s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5283703804016113s
Received healthy response to inference request in 1.7996137142181396s
Received healthy response to inference request in 1.781376838684082s
Received healthy response to inference request in 1.7344274520874023s
Received healthy response to inference request in 1.9264991283416748s
5 requests
0 failed requests
5th percentile: 1.7438173294067383
10th percentile: 1.7532072067260742
20th percentile: 1.771986961364746
30th percentile: 1.7850242137908936
40th percentile: 1.7923189640045165
50th percentile: 1.7996137142181396
60th percentile: 1.8503678798675538
70th percentile: 1.9011220455169677
80th percentile: 2.0468733787536624
90th percentile: 2.2876218795776366
95th percentile: 2.4079961299896238
99th percentile: 2.504295530319214
mean time: 1.954057502746582
Pipeline stage StressChecker completed in 11.39s
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 1.11s
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 0.76s
Shutdown handler de-registered
junhua024-chai-16-full-_69709_v8 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 5699.86s
Shutdown handler de-registered
junhua024-chai-16-full-_69709_v8 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_69709_v8 status is now torndown due to DeploymentManager action