junhua024-chai-16-full-_10179

developer_uid: junhua024

submission_id: junhua024-chai-16-full-_10179_v4

model_name: junhua024-chai-16-full-_10179_v4

model_group: junhua024/chai_16_full_1

status: torndown

timestamp: 2025-07-19T18:27:26+00:00

num_battles: 8328

num_wins: 4162

celo_rating: 1284.85

family_friendly_score: 0.5586

family_friendly_standard_error: 0.0070223363633480276

submission_type: basic

model_repo: junhua024/chai_16_full_106_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': 0.6091070904756656, 'latency_mean': 1.6416409969329835, 'latency_p50': 1.6227777004241943, 'latency_p90': 1.8081161022186278}, {'batch_size': 3, 'throughput': 1.0854846167303838, 'latency_mean': 2.7507498598098756, 'latency_p50': 2.761499285697937, 'latency_p90': 3.0216274499893188}, {'batch_size': 5, 'throughput': 1.316755337803672, 'latency_mean': 3.770592443943024, 'latency_p50': 3.7866435050964355, 'latency_p90': 4.236939120292663}, {'batch_size': 6, 'throughput': 1.37406677112268, 'latency_mean': 4.3434510409832, 'latency_p50': 4.298605799674988, 'latency_p90': 4.811772966384887}, {'batch_size': 8, 'throughput': 1.4287696816663955, 'latency_mean': 5.558044801950455, 'latency_p50': 5.61017370223999, 'latency_p90': 6.197769904136657}, {'batch_size': 10, 'throughput': 1.4833915774611062, 'latency_mean': 6.69103257060051, 'latency_p50': 6.726308465003967, 'latency_p90': 7.5146485567092896}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-16-full-_10179_v4

is_internal_developer: False

language_model: junhua024/chai_16_full_106_o_ffn_1925

model_size: 13B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-07-19

win_ratio: 0.49975984630163306

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-10179-v4-mkmlizer
Waiting for job on junhua024-chai-16-full-10179-v4-mkmlizer to finish
junhua024-chai-16-full-10179-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-10179-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-10179-v4-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-10179-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-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-10179-v4-mkmlizer: Downloaded to shared memory in 119.930s
junhua024-chai-16-full-10179-v4-mkmlizer: Checking if junhua024/chai_16_full_106_o_ffn_1925 already exists in ChaiML
junhua024-chai-16-full-10179-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv0n_i43e, device:0
junhua024-chai-16-full-10179-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-10179-v4-mkmlizer: quantized model in 31.554s
junhua024-chai-16-full-10179-v4-mkmlizer: Processed model junhua024/chai_16_full_106_o_ffn_1925 in 151.574s
junhua024-chai-16-full-10179-v4-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-10179-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-10179-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-10179-v4/nvidia
junhua024-chai-16-full-10179-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-10179-v4/nvidia/tokenizer.json
junhua024-chai-16-full-10179-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-10179-v4/nvidia/flywheel_model.0.safetensors
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)
Job junhua024-chai-16-full-10179-v4-mkmlizer completed after 182.72s with status: succeeded
Stopping job with name junhua024-chai-16-full-10179-v4-mkmlizer
Pipeline stage MKMLizer completed in 183.44s
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 junhua024-chai-16-full-10179-v4
Waiting for inference service junhua024-chai-16-full-10179-v4 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 junhua024-chai-16-full-_69709_v6: HTTPConnectionPool(host='junhua024-chai-16-full-69709-v6-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-_69709_v6: HTTPConnectionPool(host='junhua024-chai-16-full-69709-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-10179-v4 ready after 333.02913451194763s
Pipeline stage MKMLDeployer completed in 333.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.332639455795288s
Received healthy response to inference request in 1.926823616027832s
Received healthy response to inference request in 1.6372106075286865s
Received healthy response to inference request in 2.2981791496276855s
Received healthy response to inference request in 2.119237184524536s
5 requests
0 failed requests
5th percentile: 1.6951332092285156
10th percentile: 1.7530558109283447
20th percentile: 1.868901014328003
30th percentile: 1.965306329727173
40th percentile: 2.0422717571258544
50th percentile: 2.119237184524536
60th percentile: 2.190813970565796
70th percentile: 2.2623907566070556
80th percentile: 2.305071210861206
90th percentile: 2.318855333328247
95th percentile: 2.3257473945617675
99th percentile: 2.331261043548584
mean time: 2.062818002700806
Pipeline stage StressChecker completed in 11.78s
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 0.74s
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 0.68s
Shutdown handler de-registered
junhua024-chai-16-full-_10179_v4 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 3561.80s
Shutdown handler de-registered
junhua024-chai-16-full-_10179_v4 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_10179_v4 status is now torndown due to DeploymentManager action