junhua024-chai-1-full-0661

developer_uid: junhua024

submission_id: junhua024-chai-1-full-0661_v2

model_name: junhua024-chai-1-full-0661_v2

model_group: junhua024/chai_1-full_06

status: torndown

timestamp: 2025-06-29T13:10:06+00:00

num_battles: 8111

num_wins: 3617

celo_rating: 1244.73

family_friendly_score: 0.6016

family_friendly_standard_error: 0.0069235459123197845

submission_type: basic

model_repo: junhua024/chai_1-full_0661

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': 0.5981776082950285, 'latency_mean': 1.6715713119506836, 'latency_p50': 1.668243408203125, 'latency_p90': 1.8429298162460328}, {'batch_size': 3, 'throughput': 1.0820734697697434, 'latency_mean': 2.7611266839504243, 'latency_p50': 2.766993999481201, 'latency_p90': 3.0330901861190798}, {'batch_size': 5, 'throughput': 1.2925145628045156, 'latency_mean': 3.849534777402878, 'latency_p50': 3.869199514389038, 'latency_p90': 4.32448718547821}, {'batch_size': 6, 'throughput': 1.356262664526682, 'latency_mean': 4.39917946100235, 'latency_p50': 4.441972732543945, 'latency_p90': 4.902469754219055}, {'batch_size': 8, 'throughput': 1.4272763583595856, 'latency_mean': 5.5610719907283785, 'latency_p50': 5.542881369590759, 'latency_p90': 6.25073184967041}, {'batch_size': 10, 'throughput': 1.447457106929107, 'latency_mean': 6.848064746856689, 'latency_p50': 6.882517576217651, 'latency_p90': 7.643042802810669}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-0661_v2

is_internal_developer: False

language_model: junhua024/chai_1-full_0661

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-06-29

win_ratio: 0.4459376155837751

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 40, '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': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-1-full-0661-v2-mkmlizer
Waiting for job on junhua024-chai-1-full-0661-v2-mkmlizer to finish
junhua024-chai-1-full-0661-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-0661-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-0661-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-0661-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-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-1-full-0661-v2-mkmlizer: Downloaded to shared memory in 126.959s
junhua024-chai-1-full-0661-v2-mkmlizer: Checking if junhua024/chai_1-full_0661 already exists in ChaiML
junhua024-chai-1-full-0661-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpg44l986q, device:0
junhua024-chai-1-full-0661-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-0661-v2-mkmlizer: quantized model in 31.975s
junhua024-chai-1-full-0661-v2-mkmlizer: Processed model junhua024/chai_1-full_0661 in 159.008s
junhua024-chai-1-full-0661-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-0661-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-0661-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-0661-v2
junhua024-chai-1-full-0661-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-0661-v2/special_tokens_map.json
junhua024-chai-1-full-0661-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-0661-v2/config.json
junhua024-chai-1-full-0661-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-0661-v2/tokenizer_config.json
junhua024-chai-1-full-0661-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-0661-v2/tokenizer.json
junhua024-chai-1-full-0661-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-0661-v2/flywheel_model.0.safetensors
Job junhua024-chai-1-full-0661-v2-mkmlizer completed after 188.94s with status: succeeded
Stopping job with name junhua024-chai-1-full-0661-v2-mkmlizer
Pipeline stage MKMLizer completed in 189.54s
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-1-full-0661-v2
Waiting for inference service junhua024-chai-1-full-0661-v2 to be ready
Failed to get response for submission junhua024-chai-1-full-002_v30: HTTPConnectionPool(host='junhua024-chai-1-full-002-v30-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-1-full-0661-v2 ready after 180.65973281860352s
Pipeline stage MKMLDeployer completed in 181.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7204980850219727s
Received healthy response to inference request in 1.4921364784240723s
Received healthy response to inference request in 1.8301467895507812s
Received healthy response to inference request in 1.4564464092254639s
Received healthy response to inference request in 1.4532361030578613s
5 requests
0 failed requests
5th percentile: 1.4538781642913818
10th percentile: 1.4545202255249023
20th percentile: 1.4558043479919434
30th percentile: 1.4635844230651855
40th percentile: 1.477860450744629
50th percentile: 1.4921364784240723
60th percentile: 1.627340602874756
70th percentile: 1.7625447273254393
80th percentile: 2.0082170486450197
90th percentile: 2.364357566833496
95th percentile: 2.542427825927734
99th percentile: 2.684884033203125
mean time: 1.7904927730560303
Pipeline stage StressChecker completed in 10.41s
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 0.77s
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 0.80s
Shutdown handler de-registered
junhua024-chai-1-full-0661_v2 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 3215.23s
Shutdown handler de-registered
junhua024-chai-1-full-0661_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-0661_v2 status is now torndown due to DeploymentManager action