junhua024-chai-16-full-_96988

developer_uid: junhua024

submission_id: junhua024-chai-16-full-_96988_v3

model_name: junhua024-chai-16-full-_96988_v3

model_group: junhua024/chai_16_full_q

status: torndown

timestamp: 2025-07-20T08:34:12+00:00

num_battles: 8471

num_wins: 4019

celo_rating: 1270.51

family_friendly_score: 0.5502

family_friendly_standard_error: 0.007035338797812086

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': 0.6053689328953565, 'latency_mean': 1.65173712849617, 'latency_p50': 1.644299030303955, 'latency_p90': 1.8396021604537964}, {'batch_size': 3, 'throughput': 1.102689326381843, 'latency_mean': 2.709121414422989, 'latency_p50': 2.6942431926727295, 'latency_p90': 3.0010207891464233}, {'batch_size': 5, 'throughput': 1.321877978210377, 'latency_mean': 3.7620298075675964, 'latency_p50': 3.757349967956543, 'latency_p90': 4.125911116600037}, {'batch_size': 6, 'throughput': 1.3867493591654751, 'latency_mean': 4.292926596403122, 'latency_p50': 4.241046667098999, 'latency_p90': 4.823500847816467}, {'batch_size': 8, 'throughput': 1.4507168910096182, 'latency_mean': 5.484121172428131, 'latency_p50': 5.542224407196045, 'latency_p90': 6.059172558784485}, {'batch_size': 10, 'throughput': 1.4774141942629722, 'latency_mean': 6.697046900987625, 'latency_p50': 6.708556532859802, 'latency_p90': 7.555518174171448}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-16-full-_96988_v3

is_internal_developer: False

language_model: junhua024/chai_16_full_qkv106_o106_ffn106_1925

model_size: 13B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-20

win_ratio: 0.47444221461456737

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-v3-mkmlizer
Waiting for job on junhua024-chai-16-full-96988-v3-mkmlizer to finish
junhua024-chai-16-full-96988-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-96988-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-96988-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-96988-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-96988-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-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-v3-mkmlizer: Downloaded to shared memory in 123.187s
junhua024-chai-16-full-96988-v3-mkmlizer: Checking if junhua024/chai_16_full_qkv106_o106_ffn106_1925 already exists in ChaiML
junhua024-chai-16-full-96988-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpeoihgdev, device:0
junhua024-chai-16-full-96988-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-96988-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-96988-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-96988-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v3/nvidia
junhua024-chai-16-full-96988-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v3/nvidia/config.json
junhua024-chai-16-full-96988-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v3/nvidia/special_tokens_map.json
junhua024-chai-16-full-96988-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v3/nvidia/tokenizer_config.json
junhua024-chai-16-full-96988-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v3/nvidia/tokenizer.json
junhua024-chai-16-full-96988-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-96988-v3/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-16-full-96988-v3-mkmlizer completed after 190.65s with status: succeeded
Stopping job with name junhua024-chai-16-full-96988-v3-mkmlizer
Pipeline stage MKMLizer completed in 191.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-16-full-96988-v3
Waiting for inference service junhua024-chai-16-full-96988-v3 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)
Inference service junhua024-chai-16-full-96988-v3 ready after 321.12906789779663s
Pipeline stage MKMLDeployer completed in 321.84s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.635467290878296s
Received healthy response to inference request in 1.5449199676513672s
Received healthy response to inference request in 1.8378582000732422s
Received healthy response to inference request in 2.0879366397857666s
Received healthy response to inference request in 1.759631872177124s
5 requests
0 failed requests
5th percentile: 1.5878623485565186
10th percentile: 1.6308047294616699
20th percentile: 1.7166894912719726
30th percentile: 1.7752771377563477
40th percentile: 1.806567668914795
50th percentile: 1.8378582000732422
60th percentile: 1.937889575958252
70th percentile: 2.0379209518432617
80th percentile: 2.1974427700042725
90th percentile: 2.416455030441284
95th percentile: 2.52596116065979
99th percentile: 2.6135660648345946
mean time: 1.973162794113159
Pipeline stage StressChecker completed in 11.19s
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 0.66s
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 0.70s
Shutdown handler de-registered
junhua024-chai-16-full-_96988_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-16-full-96988-v3-profiler
Waiting for inference service junhua024-chai-16-full-96988-v3-profiler to be ready
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 4289.15s
Shutdown handler de-registered
junhua024-chai-16-full-_96988_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_96988_v3 status is now torndown due to DeploymentManager action