submission_id: nousresearch-meta-llama_4939_v52
developer_uid: end_to_end_test
best_of: 4
celo_rating: 1182.06
display_name: nousresearch-meta-llama_4939_v52
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_v52
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3.1-8B-Instruct
model_size: 8B
num_battles: 12341
num_wins: 5210
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-31T03:16:35+00:00
us_pacific_date: 2024-08-30
win_ratio: 0.42217000243092134
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4939-v52-mkmlizer
Waiting for job on nousresearch-meta-llama-4939-v52-mkmlizer to finish
nousresearch-meta-llama-4939-v52-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4939-v52-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║  Version: 0.10.1                                                    ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
nousresearch-meta-llama-4939-v52-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4939-v52-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4939-v52-mkmlizer: Downloaded to shared memory in 33.744s
nousresearch-meta-llama-4939-v52-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv1fgi9kt, device:0
nousresearch-meta-llama-4939-v52-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4939-v52-mkmlizer: quantized model in 25.729s
nousresearch-meta-llama-4939-v52-mkmlizer: Processed model NousResearch/Meta-Llama-3.1-8B-Instruct in 59.473s
nousresearch-meta-llama-4939-v52-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4939-v52-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4939-v52-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v52
nousresearch-meta-llama-4939-v52-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v52/config.json
nousresearch-meta-llama-4939-v52-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v52/special_tokens_map.json
nousresearch-meta-llama-4939-v52-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v52/tokenizer_config.json
nousresearch-meta-llama-4939-v52-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v52/tokenizer.json
nousresearch-meta-llama-4939-v52-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v52/flywheel_model.0.safetensors
Job nousresearch-meta-llama-4939-v52-mkmlizer completed after 87.16s with status: succeeded
Stopping job with name nousresearch-meta-llama-4939-v52-mkmlizer
Pipeline stage MKMLizer completed in 88.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.26s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service nousresearch-meta-llama-4939-v52
Waiting for inference service nousresearch-meta-llama-4939-v52 to be ready
Inference service nousresearch-meta-llama-4939-v52 ready after 171.60425281524658s
Pipeline stage MKMLDeployer completed in 172.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7926719188690186s
Received healthy response to inference request in 1.512542963027954s
Received healthy response to inference request in 1.2202742099761963s
Received healthy response to inference request in 1.094951868057251s
Received healthy response to inference request in 1.200387954711914s
5 requests
0 failed requests
5th percentile: 1.1160390853881836
10th percentile: 1.1371263027191163
20th percentile: 1.1793007373809814
30th percentile: 1.2043652057647705
40th percentile: 1.2123197078704835
50th percentile: 1.2202742099761963
60th percentile: 1.3371817111968993
70th percentile: 1.4540892124176026
80th percentile: 1.568568754196167
90th percentile: 1.6806203365325927
95th percentile: 1.7366461277008056
99th percentile: 1.781466760635376
mean time: 1.3641657829284668
Pipeline stage StressChecker completed in 9.01s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 3.22s
nousresearch-meta-llama_4939_v52 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service nousresearch-meta-llama-4939-v52-profiler
Waiting for inference service nousresearch-meta-llama-4939-v52-profiler to be ready
Inference service nousresearch-meta-llama-4939-v52-profiler ready after 190.44692301750183s
Pipeline stage MKMLProfilerDeployer completed in 190.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.33s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service nousresearch-meta-llama-4939-v52-profiler is running
Tearing down inference service nousresearch-meta-llama-4939-v52-profiler
Service nousresearch-meta-llama-4939-v52-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.83s
nousresearch-meta-llama_4939_v52 status is now inactive due to auto deactivation removed underperforming models
nousresearch-meta-llama_4939_v52 status is now torndown due to DeploymentManager action