developer_uid: junhua024
submission_id: junhua024-chai-16-full-_63690_v8
model_name: junhua024-chai-16-full-_63690_v8
model_group: junhua024/chai_16_full_1
status: torndown
timestamp: 2025-07-20T05:15:15+00:00
num_battles: 5186
num_wins: 2750
celo_rating: 1290.56
family_friendly_score: 0.5534
family_friendly_standard_error: 0.007030625007778469
submission_type: basic
model_repo: junhua024/chai_16_full_106_qkv_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': 0.5911699177525611, 'latency_mean': 1.6913650381565093, 'latency_p50': 1.7030078172683716, 'latency_p90': 1.8427886486053466}, {'batch_size': 3, 'throughput': 1.0640450321450163, 'latency_mean': 2.8109780669212343, 'latency_p50': 2.8023014068603516, 'latency_p90': 3.0919829845428466}, {'batch_size': 5, 'throughput': 1.2707523776264666, 'latency_mean': 3.910537085533142, 'latency_p50': 3.919683814048767, 'latency_p90': 4.33527889251709}, {'batch_size': 6, 'throughput': 1.3357744067428265, 'latency_mean': 4.4702294051647185, 'latency_p50': 4.480135679244995, 'latency_p90': 5.064768624305725}, {'batch_size': 8, 'throughput': 1.3884316198294526, 'latency_mean': 5.720608279705048, 'latency_p50': 5.731479167938232, 'latency_p90': 6.5703489780426025}, {'batch_size': 10, 'throughput': 1.4222589202177376, 'latency_mean': 6.987130267620087, 'latency_p50': 6.936428546905518, 'latency_p90': 7.940860414505005}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-16-full-_63690_v8
is_internal_developer: False
language_model: junhua024/chai_16_full_106_qkv_o_ffn_1925
model_size: 13B
ranking_group: single
throughput_3p7s: 1.25
us_pacific_date: 2025-07-19
win_ratio: 0.5302738141149248
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-63690-v8-mkmlizer
Waiting for job on junhua024-chai-16-full-63690-v8-mkmlizer to finish
junhua024-chai-16-full-63690-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-63690-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-63690-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-63690-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-63690-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 junhua024-chai-16-full-_63690_v3: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-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-63690-v8-mkmlizer: quantized model in 32.050s
junhua024-chai-16-full-63690-v8-mkmlizer: Processed model junhua024/chai_16_full_106_qkv_o_ffn_1925 in 111.210s
junhua024-chai-16-full-63690-v8-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-63690-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-63690-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-63690-v8/nvidia
junhua024-chai-16-full-63690-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-63690-v8/nvidia/config.json
junhua024-chai-16-full-63690-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-63690-v8/nvidia/special_tokens_map.json
junhua024-chai-16-full-63690-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-63690-v8/nvidia/tokenizer_config.json
junhua024-chai-16-full-63690-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-63690-v8/nvidia/tokenizer.json
Job junhua024-chai-16-full-63690-v8-mkmlizer completed after 140.08s with status: succeeded
Stopping job with name junhua024-chai-16-full-63690-v8-mkmlizer
Pipeline stage MKMLizer completed in 141.25s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-16-full-63690-v8
Waiting for inference service junhua024-chai-16-full-63690-v8 to be ready
Failed to get response for submission junhua024-chai-16-full-_63690_v3: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v3: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-63690-v8 ready after 331.6710982322693s
Pipeline stage MKMLDeployer completed in 332.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3069612979888916s
Received healthy response to inference request in 1.7687678337097168s
Received healthy response to inference request in 1.5802252292633057s
Received healthy response to inference request in 1.8874330520629883s
Received healthy response to inference request in 1.5107336044311523s
5 requests
0 failed requests
5th percentile: 1.524631929397583
10th percentile: 1.5385302543640136
20th percentile: 1.566326904296875
30th percentile: 1.617933750152588
40th percentile: 1.6933507919311523
50th percentile: 1.7687678337097168
60th percentile: 1.8162339210510254
70th percentile: 1.863700008392334
80th percentile: 1.9713387012481691
90th percentile: 2.1391499996185304
95th percentile: 2.2230556488037108
99th percentile: 2.2901801681518554
mean time: 1.810824203491211
Pipeline stage StressChecker completed in 11.11s
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 0.72s
Shutdown handler de-registered
junhua024-chai-16-full-_63690_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3233.03s
Shutdown handler de-registered
junhua024-chai-16-full-_63690_v8 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_63690_v8 status is now torndown due to DeploymentManager action