submission_id: sao10k-llama-3-1-8b-sthe_7811_v3
developer_uid: sao10k
alignment_samples: 12313
alignment_score: -0.5633127463466018
best_of: 8
celo_rating: 1221.86
display_name: Stheno-341
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '<|eot_id|>', '\n\n{user_name}', '\nYou:', '<|end_header_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Sao10K/Llama-3.1-8B-Stheno-v3.4
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Sao10K/Llama-3.1-8B-Sthe
model_name: Stheno-341
model_num_parameters: 8030261248.0
model_repo: Sao10K/Llama-3.1-8B-Stheno-v3.4
model_size: 8B
num_battles: 12313
num_wins: 5967
propriety_score: 0.7097933513027853
propriety_total_count: 1113.0
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-19T17:43:25+00:00
us_pacific_date: 2024-08-19
win_ratio: 0.4846097620401202
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer
Waiting for job on sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer to finish
Stopping job with name sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer
%s, retrying in %s seconds...
Starting job with name sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer
Waiting for job on sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer to finish
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ _____ __ __ ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ /___/ ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ Version: 0.9.11 ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ https://mk1.ai ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ belonging to: ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ Chai Research Corp. ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ║ ║
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: Downloaded to shared memory in 31.281s
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa9eaanif, device:0
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: quantized model in 26.414s
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: Processed model Sao10K/Llama-3.1-8B-Stheno-v3.4 in 57.695s
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: creating bucket guanaco-mkml-models
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-llama-3-1-8b-sthe-7811-v3
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-llama-3-1-8b-sthe-7811-v3/special_tokens_map.json
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-llama-3-1-8b-sthe-7811-v3/config.json
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-llama-3-1-8b-sthe-7811-v3/tokenizer_config.json
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-llama-3-1-8b-sthe-7811-v3/tokenizer.json
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-llama-3-1-8b-sthe-7811-v3/flywheel_model.0.safetensors
sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 35.59it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:05, 46.58it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:04, 54.97it/s] Loading 0: 10%|▉ | 28/291 [00:00<00:06, 40.37it/s] Loading 0: 11%|█▏ | 33/291 [00:00<00:06, 40.79it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:05, 47.06it/s] Loading 0: 16%|█▌ | 46/291 [00:01<00:05, 46.20it/s] Loading 0: 18%|█▊ | 51/291 [00:01<00:05, 46.36it/s] Loading 0: 21%|██ | 60/291 [00:01<00:04, 51.27it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:05, 41.60it/s] Loading 0: 25%|██▍ | 72/291 [00:01<00:05, 40.24it/s] Loading 0: 26%|██▋ | 77/291 [00:01<00:05, 40.54it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:04, 48.95it/s] Loading 0: 31%|███▏ | 91/291 [00:02<00:04, 47.57it/s] Loading 0: 33%|███▎ | 96/291 [00:02<00:04, 46.51it/s] Loading 0: 35%|███▍ | 101/291 [00:02<00:04, 38.66it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:04, 38.99it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 43.00it/s] Loading 0: 41%|████ | 118/291 [00:02<00:04, 42.37it/s] Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 42.98it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 49.67it/s] Loading 0: 47%|████▋ | 136/291 [00:03<00:03, 47.61it/s] Loading 0: 49%|████▉ | 142/291 [00:03<00:03, 40.48it/s] Loading 0: 51%|█████ | 147/291 [00:03<00:03, 40.42it/s] Loading 0: 52%|█████▏ | 152/291 [00:03<00:03, 42.27it/s] Loading 0: 54%|█████▍ | 158/291 [00:03<00:03, 39.07it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 47.22it/s] Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 45.05it/s] Loading 0: 61%|██████ | 177/291 [00:04<00:02, 44.37it/s] Loading 0: 63%|██████▎ | 182/291 [00:04<00:02, 38.96it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:02, 38.81it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:02, 42.63it/s] Loading 0: 68%|██████▊ | 199/291 [00:04<00:02, 41.95it/s] Loading 0: 70%|███████ | 204/291 [00:04<00:02, 42.48it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 47.81it/s] Loading 0: 75%|███████▍ | 217/291 [00:04<00:01, 45.72it/s] Loading 0: 77%|███████▋ | 223/291 [00:05<00:01, 40.22it/s] Loading 0: 78%|███████▊ | 228/291 [00:05<00:01, 40.49it/s] Loading 0: 80%|████████ | 233/291 [00:05<00:01, 41.51it/s] Loading 0: 82%|████████▏ | 239/291 [00:05<00:01, 38.92it/s] Loading 0: 85%|████████▍ | 246/291 [00:05<00:00, 45.79it/s] Loading 0: 86%|████████▋ | 251/291 [00:05<00:00, 45.56it/s] Loading 0: 88%|████████▊ | 257/291 [00:05<00:00, 41.69it/s] Loading 0: 90%|█████████ | 263/291 [00:06<00:00, 39.56it/s] Loading 0: 92%|█████████▏| 268/291 [00:06<00:00, 39.65it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 41.95it/s] Loading 0: 96%|█████████▌| 278/291 [00:06<00:00, 43.67it/s] Loading 0: 98%|█████████▊| 284/291 [00:06<00:00, 41.58it/s] Loading 0: 100%|██████████| 291/291 [00:11<00:00, 3.53it/s]
Job sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer completed after 84.06s with status: succeeded
Stopping job with name sao10k-llama-3-1-8b-sthe-7811-v3-mkmlizer
Pipeline stage MKMLizer completed in 85.57s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service sao10k-llama-3-1-8b-sthe-7811-v3
Waiting for inference service sao10k-llama-3-1-8b-sthe-7811-v3 to be ready
Inference service sao10k-llama-3-1-8b-sthe-7811-v3 ready after 241.87334728240967s
Pipeline stage ISVCDeployer completed in 242.63s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.19909405708313s
Received healthy response to inference request in 1.5253562927246094s
Received healthy response to inference request in 1.6843531131744385s
Received healthy response to inference request in 1.3736248016357422s
Received healthy response to inference request in 1.419288158416748s
5 requests
0 failed requests
5th percentile: 1.3827574729919434
10th percentile: 1.3918901443481446
20th percentile: 1.4101554870605468
30th percentile: 1.4405017852783204
40th percentile: 1.4829290390014649
50th percentile: 1.5253562927246094
60th percentile: 1.588955020904541
70th percentile: 1.6525537490844726
80th percentile: 1.7873013019561768
90th percentile: 1.9931976795196533
95th percentile: 2.0961458683013916
99th percentile: 2.1785044193267824
mean time: 1.6403432846069337
Pipeline stage StressChecker completed in 8.93s
sao10k-llama-3-1-8b-sthe_7811_v3 status is now deployed due to DeploymentManager action
sao10k-llama-3-1-8b-sthe_7811_v3 status is now inactive due to auto deactivation removed underperforming models
sao10k-llama-3-1-8b-sthe_7811_v3 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics