submission_id: nousresearch-meta-llama_4939_v40
developer_uid: end_to_end_test
best_of: 4
display_name: nousresearch-meta-llama_4939_v40
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_v40
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3.1-8B-Instruct
model_size: 8B
num_battles: 352
num_wins: 153
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-30T20:39:10+00:00
us_pacific_date: 2024-08-30
win_ratio: 0.4346590909090909
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Pipeline stage MKMLModelDeleter completed in 15.32s
Starting job with name nousresearch-meta-llama-4939-v40-mkmlizer
nousresearch-meta-llama_4939_v39 status is now torndown due to DeploymentManager action
Waiting for job on nousresearch-meta-llama-4939-v40-mkmlizer to finish
nousresearch-meta-llama-4939-v40-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4939-v40-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ Version: 0.10.1 ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
nousresearch-meta-llama-4939-v40-mkmlizer: ║ ║
nousresearch-meta-llama-4939-v40-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4939-v40-mkmlizer: Downloaded to shared memory in 36.209s
nousresearch-meta-llama-4939-v40-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyveresh_, device:0
nousresearch-meta-llama-4939-v40-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4939-v40-mkmlizer: quantized model in 25.882s
nousresearch-meta-llama-4939-v40-mkmlizer: Processed model NousResearch/Meta-Llama-3.1-8B-Instruct in 62.092s
nousresearch-meta-llama-4939-v40-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4939-v40-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4939-v40-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v40
nousresearch-meta-llama-4939-v40-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v40/config.json
nousresearch-meta-llama-4939-v40-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v40/special_tokens_map.json
nousresearch-meta-llama-4939-v40-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v40/tokenizer_config.json
nousresearch-meta-llama-4939-v40-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4939-v40/tokenizer.json
Job nousresearch-meta-llama-4939-v40-mkmlizer completed after 87.77s with status: succeeded
Stopping job with name nousresearch-meta-llama-4939-v40-mkmlizer
Pipeline stage MKMLizer completed in 89.18s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.28s
Running pipeline stage MKMLDeployer
Creating inference service nousresearch-meta-llama-4939-v40
Waiting for inference service nousresearch-meta-llama-4939-v40 to be ready
Inference service nousresearch-meta-llama-4939-v40 ready after 181.66542196273804s
Pipeline stage MKMLDeployer completed in 182.51s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1257131099700928s
Received healthy response to inference request in 1.4268298149108887s
Received healthy response to inference request in 1.7321760654449463s
Received healthy response to inference request in 1.8347430229187012s
Received healthy response to inference request in 1.8166630268096924s
5 requests
0 failed requests
5th percentile: 1.4878990650177002
10th percentile: 1.5489683151245117
20th percentile: 1.6711068153381348
30th percentile: 1.7490734577178955
40th percentile: 1.782868242263794
50th percentile: 1.8166630268096924
60th percentile: 1.823895025253296
70th percentile: 1.8311270236968995
80th percentile: 1.8929370403289796
90th percentile: 2.009325075149536
95th percentile: 2.0675190925598144
99th percentile: 2.114074306488037
mean time: 1.7872250080108643
Pipeline stage StressChecker completed in 11.32s
nousresearch-meta-llama_4939_v40 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4939_v40 status is now inactive due to admin request
Waiting for job on nousresearch-meta-llama-4939-v41-mkmlizer to finish
nousresearch-meta-llama_4939_v40 status is now torndown due to DeploymentManager action