junhua024-chai-1-full_94469

developer_uid: junhua024

submission_id: junhua024-chai-1-full_94469_v116

model_name: junhua024-chai-1-full_94469_v116

model_group: junhua024/chai-1-full-06

status: torndown

timestamp: 2025-07-17T20:26:11+00:00

num_battles: 7316

num_wins: 3542

celo_rating: 1273.77

family_friendly_score: 0.5524

family_friendly_standard_error: 0.007032129691636808

submission_type: basic

model_repo: junhua024/chai-1-full-066126

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': 0.604988541541221, 'latency_mean': 1.6527414870262147, 'latency_p50': 1.6425535678863525, 'latency_p90': 1.8377919435501098}, {'batch_size': 3, 'throughput': 1.0793855382559059, 'latency_mean': 2.765412460565567, 'latency_p50': 2.7566107511520386, 'latency_p90': 3.0410465717315676}, {'batch_size': 5, 'throughput': 1.2906756101398258, 'latency_mean': 3.84549861907959, 'latency_p50': 3.8780791759490967, 'latency_p90': 4.291530752182007}, {'batch_size': 6, 'throughput': 1.3547850440142732, 'latency_mean': 4.399225298166275, 'latency_p50': 4.388218641281128, 'latency_p90': 4.931788444519043}, {'batch_size': 8, 'throughput': 1.4253785024043601, 'latency_mean': 5.575469819307327, 'latency_p50': 5.6522216796875, 'latency_p90': 6.355239081382751}, {'batch_size': 10, 'throughput': 1.4613829310308921, 'latency_mean': 6.782937307357788, 'latency_p50': 6.736863017082214, 'latency_p90': 7.643323707580566}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full_94469_v116

is_internal_developer: False

language_model: junhua024/chai-1-full-066126

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-07-17

win_ratio: 0.4841443411700383

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-1-full-94469-v116-mkmlizer
Waiting for job on junhua024-chai-1-full-94469-v116-mkmlizer to finish
junhua024-chai-1-full-94469-v116-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-94469-v116-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-94469-v116-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v116-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-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-94469-v116-mkmlizer: Downloaded to shared memory in 80.889s
junhua024-chai-1-full-94469-v116-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-94469-v116-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpciscoatr, device:0
junhua024-chai-1-full-94469-v116-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-94469-v116-mkmlizer: quantized model in 31.001s
junhua024-chai-1-full-94469-v116-mkmlizer: Processed model junhua024/chai-1-full-066126 in 111.965s
junhua024-chai-1-full-94469-v116-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-94469-v116-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-94469-v116-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v116/nvidia
junhua024-chai-1-full-94469-v116-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v116/nvidia/config.json
junhua024-chai-1-full-94469-v116-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v116/nvidia/special_tokens_map.json
junhua024-chai-1-full-94469-v116-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v116/nvidia/tokenizer_config.json
junhua024-chai-1-full-94469-v116-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v116/nvidia/tokenizer.json
junhua024-chai-1-full-94469-v116-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v116/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-1-full-94469-v116-mkmlizer completed after 141.03s with status: succeeded
Stopping job with name junhua024-chai-1-full-94469-v116-mkmlizer
Pipeline stage MKMLizer completed in 141.76s
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-94469-v116
Waiting for inference service junhua024-chai-1-full-94469-v116 to be ready
Failed to get response for submission zmeeks-capitanito-54-3000_v5: ('http://zmeeks-capitanito-54-3000-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:56526->127.0.0.1:8080: read: connection reset by peer\n')
Inference service junhua024-chai-1-full-94469-v116 ready after 312.62916827201843s
Pipeline stage MKMLDeployer completed in 313.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5511326789855957s
Received healthy response to inference request in 1.6648764610290527s
Received healthy response to inference request in 1.683025598526001s
Received healthy response to inference request in 1.9930696487426758s
Received healthy response to inference request in 2.1334242820739746s
5 requests
0 failed requests
5th percentile: 1.6685062885284423
10th percentile: 1.672136116027832
20th percentile: 1.6793957710266114
30th percentile: 1.745034408569336
40th percentile: 1.869052028656006
50th percentile: 1.9930696487426758
60th percentile: 2.0492115020751953
70th percentile: 2.105353355407715
80th percentile: 2.216965961456299
90th percentile: 2.384049320220947
95th percentile: 2.467590999603271
99th percentile: 2.534424343109131
mean time: 2.00510573387146
Pipeline stage StressChecker completed in 11.50s
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 0.82s
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 0.77s
Shutdown handler de-registered
junhua024-chai-1-full_94469_v116 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 5307.75s
Shutdown handler de-registered
junhua024-chai-1-full_94469_v116 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full_94469_v116 status is now torndown due to DeploymentManager action
junhua024-chai-1-full_94469_v116 status is now torndown due to DeploymentManager action