junhua024-chai-1-full-066122

developer_uid: junhua024

submission_id: junhua024-chai-1-full-066122_v2

model_name: junhua024-chai-1-full-066122_v2

model_group: junhua024/chai_1-full_06

status: torndown

timestamp: 2025-06-29T19:00:55+00:00

num_battles: 6543

num_wins: 3187

celo_rating: 1266.91

family_friendly_score: 0.5498000000000001

family_friendly_standard_error: 0.007035907333102107

submission_type: basic

model_repo: junhua024/chai_1-full_066122

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': 0.590237594053644, 'latency_mean': 1.6941096460819245, 'latency_p50': 1.6932940483093262, 'latency_p90': 1.8713990688323974}, {'batch_size': 3, 'throughput': 1.0646094197515137, 'latency_mean': 2.812319818735123, 'latency_p50': 2.8376059532165527, 'latency_p90': 3.0698105812072756}, {'batch_size': 5, 'throughput': 1.2900599915924573, 'latency_mean': 3.853133836984634, 'latency_p50': 3.8679224252700806, 'latency_p90': 4.325953435897827}, {'batch_size': 6, 'throughput': 1.3423283316702315, 'latency_mean': 4.435136970281601, 'latency_p50': 4.439687609672546, 'latency_p90': 4.9427910327911375}, {'batch_size': 8, 'throughput': 1.4147538467515222, 'latency_mean': 5.613225867748261, 'latency_p50': 5.68143904209137, 'latency_p90': 6.221996474266052}, {'batch_size': 10, 'throughput': 1.435432521659069, 'latency_mean': 6.906713768243789, 'latency_p50': 6.909116864204407, 'latency_p90': 7.757103109359742}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-066122_v2

is_internal_developer: False

language_model: junhua024/chai_1-full_066122

model_size: 13B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-06-29

win_ratio: 0.4870854348158337

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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-066122-v2-mkmlizer
Waiting for job on junhua024-chai-1-full-066122-v2-mkmlizer to finish
junhua024-chai-1-full-066122-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-066122-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-066122-v2-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066122-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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`
Failed to get response for submission nitral-ai-captain-bmo-12b_v75: HTTPConnectionPool(host='nitral-ai-captain-bmo-12b-v75-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-1-full-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-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-066122-v2-mkmlizer: Downloaded to shared memory in 150.464s
junhua024-chai-1-full-066122-v2-mkmlizer: Checking if junhua024/chai_1-full_066122 already exists in ChaiML
junhua024-chai-1-full-066122-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7gxjckxt, device:0
junhua024-chai-1-full-066122-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-066122-v2-mkmlizer: quantized model in 31.362s
junhua024-chai-1-full-066122-v2-mkmlizer: Processed model junhua024/chai_1-full_066122 in 181.905s
junhua024-chai-1-full-066122-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-066122-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-066122-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-066122-v2
junhua024-chai-1-full-066122-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066122-v2/config.json
junhua024-chai-1-full-066122-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-066122-v2/special_tokens_map.json
junhua024-chai-1-full-066122-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066122-v2/tokenizer_config.json
junhua024-chai-1-full-066122-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-066122-v2/tokenizer.json
Job junhua024-chai-1-full-066122-v2-mkmlizer completed after 208.67s with status: succeeded
Stopping job with name junhua024-chai-1-full-066122-v2-mkmlizer
Pipeline stage MKMLizer completed in 209.19s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-066122-v2
Waiting for inference service junhua024-chai-1-full-066122-v2 to be ready
Failed to get response for submission nitral-ai-captain-bmo-12b_v75: HTTPConnectionPool(host='nitral-ai-captain-bmo-12b-v75-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nitral-ai-captain-bmo-12b_v75: HTTPConnectionPool(host='nitral-ai-captain-bmo-12b-v75-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-1-full-066122-v2 ready after 181.37584328651428s
Pipeline stage MKMLDeployer completed in 182.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.538123369216919s
Received healthy response to inference request in 2.023419141769409s
Received healthy response to inference request in 1.8698503971099854s
Received healthy response to inference request in 2.060059070587158s
Received healthy response to inference request in 1.6783950328826904s
5 requests
0 failed requests
5th percentile: 1.7166861057281495
10th percentile: 1.7549771785736084
20th percentile: 1.8315593242645263
30th percentile: 1.90056414604187
40th percentile: 1.9619916439056397
50th percentile: 2.023419141769409
60th percentile: 2.0380751132965087
70th percentile: 2.052731084823608
80th percentile: 2.1556719303131104
90th percentile: 2.3468976497650145
95th percentile: 2.4425105094909667
99th percentile: 2.5190007972717283
mean time: 2.0339694023132324
Pipeline stage StressChecker completed in 12.02s
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 0.64s
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 0.85s
Shutdown handler de-registered
junhua024-chai-1-full-066122_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 3412.40s
Shutdown handler de-registered
junhua024-chai-1-full-066122_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-066122_v2 status is now torndown due to DeploymentManager action