submission_id: nousresearch-meta-llama_4939_v41
developer_uid: end_to_end_test
best_of: 4
celo_rating: 1188.62
display_name: nousresearch-meta-llama_4939_v41
family_friendly_score: 0.0
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}
generation_params: {'temperature': 1.0, 'top_p': 0.99, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
ineligible_reason: model is only for e2e test
is_internal_developer: True
language_model: NousResearch/Meta-Llama-3.1-8B-Instruct
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: NousResearch/Meta-Llama-
model_name: nousresearch-meta-llama_4939_v41
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3.1-8B-Instruct
model_size: 8B
num_battles: 3365
num_wins: 1454
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-30T20:50:58+00:00
us_pacific_date: 2024-08-30
win_ratio: 0.4320950965824666
Download Preference Data
Resubmit model
Deleting key nousresearch-meta-llama-4939-v40/tokenizer.json from bucket guanaco-mkml-models
Running pipeline stage MKMLizer
Deleting key nousresearch-meta-llama-4939-v40/tokenizer_config.json from bucket guanaco-mkml-models
Starting job with name nousresearch-meta-llama-4939-v41-mkmlizer
Pipeline stage MKMLModelDeleter completed in 7.54s
nousresearch-meta-llama_4939_v40 status is now torndown due to DeploymentManager action
nousresearch-meta-llama-4939-v41-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4939-v41-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║  Version: 0.10.1                                                    ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
nousresearch-meta-llama-4939-v41-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v41-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4939-v41-mkmlizer: Downloaded to shared memory in 36.434s
nousresearch-meta-llama-4939-v41-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_64tdovk, device:0
nousresearch-meta-llama-4939-v41-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4939-v41-mkmlizer: quantized model in 26.396s
nousresearch-meta-llama-4939-v41-mkmlizer: Processed model NousResearch/Meta-Llama-3.1-8B-Instruct in 62.831s
nousresearch-meta-llama-4939-v41-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4939-v41-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4939-v41-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v41
nousresearch-meta-llama-4939-v41-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v41/config.json
nousresearch-meta-llama-4939-v41-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v41/special_tokens_map.json
nousresearch-meta-llama-4939-v41-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v41/tokenizer_config.json
nousresearch-meta-llama-4939-v41-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v41/tokenizer.json
Job nousresearch-meta-llama-4939-v41-mkmlizer completed after 87.09s with status: succeeded
Stopping job with name nousresearch-meta-llama-4939-v41-mkmlizer
Pipeline stage MKMLizer completed in 88.52s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.25s
Running pipeline stage MKMLDeployer
Creating inference service nousresearch-meta-llama-4939-v41
Waiting for inference service nousresearch-meta-llama-4939-v41 to be ready
Inference service nousresearch-meta-llama-4939-v41 ready after 191.9838719367981s
Pipeline stage MKMLDeployer completed in 192.77s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.177745819091797s
Received healthy response to inference request in 1.4383831024169922s
Received healthy response to inference request in 1.6339082717895508s
Received healthy response to inference request in 1.3589539527893066s
Received healthy response to inference request in 1.5041422843933105s
5 requests
0 failed requests
5th percentile: 1.3748397827148438
10th percentile: 1.3907256126403809
20th percentile: 1.422497272491455
30th percentile: 1.4515349388122558
40th percentile: 1.4778386116027833
50th percentile: 1.5041422843933105
60th percentile: 1.5560486793518067
70th percentile: 1.6079550743103028
80th percentile: 1.74267578125
90th percentile: 1.9602108001708984
95th percentile: 2.0689783096313477
99th percentile: 2.155992317199707
mean time: 1.6226266860961913
Pipeline stage StressChecker completed in 10.99s
nousresearch-meta-llama_4939_v41 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4939_v41 status is now inactive due to admin request
Running pipeline stage MKMLizer
nousresearch-meta-llama_4939_v41 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLProfilerTemplater
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.44s
Running pipeline stage MKMLProfilerDeployer
Creating inference service nousresearch-meta-llama-4939-v41-profiler
Waiting for inference service nousresearch-meta-llama-4939-v41-profiler to be ready
Tearing down inference service nousresearch-meta-llama-4939-v41-profiler
%s, retrying in %s seconds...
Creating inference service nousresearch-meta-llama-4939-v41-profiler
Waiting for inference service nousresearch-meta-llama-4939-v41-profiler to be ready