submission_id: chaiml-lexical-nemov8-1k1e5_v7
developer_uid: Jellywibble
alignment_samples: 11234
alignment_score: 2.55377377185818
best_of: 4
celo_rating: 1187.03
display_name: extreme-fluffy
formatter: {'memory_template': 'You are roleplaying as {bot_name} extreme cute and fluffy edition. Every sentence you say makes you extremely cute and fluffy, to the extend that people want to pet you for your fluffiness.', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name} [Extreme Cute & Fluffy Edition]:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: True
language_model: ChaiML/Lexical-Nemov8-1k1e5
latencies: [{'batch_size': 1, 'throughput': 0.6395295433473102, 'latency_mean': 1.5635856068134308, 'latency_p50': 1.5646032094955444, 'latency_p90': 1.7306676864624022}, {'batch_size': 3, 'throughput': 1.254380587610576, 'latency_mean': 2.3847789800167085, 'latency_p50': 2.3714394569396973, 'latency_p90': 2.6528448820114137}, {'batch_size': 5, 'throughput': 1.5533071206757256, 'latency_mean': 3.19921528339386, 'latency_p50': 3.2208564281463623, 'latency_p90': 3.597749066352844}, {'batch_size': 6, 'throughput': 1.6369842196674846, 'latency_mean': 3.651213232278824, 'latency_p50': 3.6652361154556274, 'latency_p90': 4.128097438812256}, {'batch_size': 8, 'throughput': 1.75601473933972, 'latency_mean': 4.523809875249863, 'latency_p50': 4.559533476829529, 'latency_p90': 5.094976234436035}, {'batch_size': 10, 'throughput': 1.7850554452022154, 'latency_mean': 5.557128129005432, 'latency_p50': 5.5432398319244385, 'latency_p90': 6.333705043792724}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: ChaiML/Lexical-Nemov8-1k
model_name: extreme-fluffy
model_num_parameters: 12772070400.0
model_repo: ChaiML/Lexical-Nemov8-1k1e5
model_size: 13B
num_battles: 11233
num_wins: 4808
propriety_score: 0.7533960292580982
propriety_total_count: 957.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.65
timestamp: 2024-09-04T17:35:32+00:00
us_pacific_date: 2024-09-04
win_ratio: 0.4280245704620315
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-lexical-nemov8-1k1e5-v7-mkmlizer
Waiting for job on chaiml-lexical-nemov8-1k1e5-v7-mkmlizer to finish
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ _____ __ __ ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ /___/ ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ Version: 0.10.1 ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ https://mk1.ai ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ belonging to: ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ Chai Research Corp. ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ║ ║
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: Downloaded to shared memory in 72.497s
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9p_jjxc9, device:0
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: quantized model in 40.310s
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: Processed model ChaiML/Lexical-Nemov8-1k1e5 in 112.806s
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v7
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v7/config.json
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v7/special_tokens_map.json
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v7/tokenizer_config.json
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v7/tokenizer.json
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-lexical-nemov8-1k1e5-v7/flywheel_model.0.safetensors
chaiml-lexical-nemov8-1k1e5-v7-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 22.24it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 28.19it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:13, 25.49it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:10, 31.87it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:14, 23.85it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:15, 21.30it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:12, 27.05it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:11, 28.96it/s] Loading 0: 11%|█ | 39/363 [00:01<00:10, 30.71it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:10, 29.22it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 30.63it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 28.49it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:10, 29.78it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:12, 24.86it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 21.71it/s] Loading 0: 19%|█▉ | 69/363 [00:02<00:10, 27.04it/s] Loading 0: 20%|██ | 73/363 [00:02<00:10, 27.67it/s] Loading 0: 21%|██ | 77/363 [00:02<00:11, 24.83it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:09, 29.54it/s] Loading 0: 24%|██▎ | 86/363 [00:03<00:10, 26.27it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 32.90it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:08, 31.70it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:10, 25.99it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:11, 22.35it/s] Loading 0: 31%|███ | 111/363 [00:04<00:08, 29.09it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:08, 27.88it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:08, 29.62it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 28.16it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 30.25it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 29.48it/s] Loading 0: 38%|███▊ | 137/363 [00:04<00:07, 29.03it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 25.58it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:09, 23.59it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 22.85it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:07, 28.99it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:07, 28.43it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:06, 31.44it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 30.37it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:05, 32.69it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 30.15it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 24.45it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:08, 21.60it/s] Loading 0: 53%|█████▎ | 192/363 [00:06<00:05, 29.17it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:05, 28.11it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 31.39it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 30.65it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 32.06it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:04, 30.11it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:04, 30.85it/s] Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 25.88it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 24.68it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 23.83it/s] Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 30.84it/s] Loading 0: 66%|██████▋ | 241/363 [00:08<00:04, 29.25it/s] Loading 0: 68%|██████▊ | 246/363 [00:08<00:03, 32.08it/s] Loading 0: 69%|██████▉ | 250/363 [00:08<00:03, 30.71it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 31.86it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 30.00it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:04, 24.51it/s] Loading 0: 73%|███████▎ | 266/363 [00:09<00:04, 21.59it/s] Loading 0: 75%|███████▌ | 273/363 [00:09<00:03, 28.80it/s] Loading 0: 76%|███████▋ | 277/363 [00:09<00:03, 28.29it/s] Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 30.77it/s] Loading 0: 79%|███████▉ | 286/363 [00:10<00:02, 29.27it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 31.77it/s] Loading 0: 81%|████████▏ | 295/363 [00:10<00:02, 30.28it/s] Loading 0: 82%|████████▏ | 299/363 [00:10<00:02, 31.05it/s] Loading 0: 84%|████████▎ | 304/363 [00:10<00:02, 26.83it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 25.38it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 23.79it/s] Loading 0: 87%|████████▋ | 316/363 [00:11<00:01, 28.92it/s] Loading 0: 88%|████████▊ | 320/363 [00:11<00:01, 25.42it/s] Loading 0: 90%|████████▉ | 325/363 [00:11<00:01, 30.10it/s] Loading 0: 91%|█████████ | 329/363 [00:11<00:01, 26.31it/s] Loading 0: 93%|█████████▎| 336/363 [00:11<00:00, 32.65it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 30.98it/s] Loading 0: 95%|█████████▍| 344/363 [00:19<00:09, 2.08it/s] Loading 0: 96%|█████████▌| 348/363 [00:19<00:05, 2.76it/s] Loading 0: 97%|█████████▋| 353/363 [00:19<00:02, 3.95it/s] Loading 0: 98%|█████████▊| 357/363 [00:19<00:01, 5.08it/s]
Job chaiml-lexical-nemov8-1k1e5-v7-mkmlizer completed after 136.29s with status: succeeded
Stopping job with name chaiml-lexical-nemov8-1k1e5-v7-mkmlizer
Pipeline stage MKMLizer completed in 137.81s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-lexical-nemov8-1k1e5-v7
Waiting for inference service chaiml-lexical-nemov8-1k1e5-v7 to be ready
Inference service chaiml-lexical-nemov8-1k1e5-v7 ready after 141.17422533035278s
Pipeline stage MKMLDeployer completed in 141.78s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.661184549331665s
Received healthy response to inference request in 2.0221304893493652s
Received healthy response to inference request in 1.566704273223877s
Received healthy response to inference request in 1.4862725734710693s
Received healthy response to inference request in 1.9335641860961914s
5 requests
0 failed requests
5th percentile: 1.5023589134216309
10th percentile: 1.5184452533721924
20th percentile: 1.5506179332733154
30th percentile: 1.64007625579834
40th percentile: 1.7868202209472657
50th percentile: 1.9335641860961914
60th percentile: 1.9689907073974608
70th percentile: 2.0044172286987303
80th percentile: 2.1499413013458253
90th percentile: 2.405562925338745
95th percentile: 2.533373737335205
99th percentile: 2.635622386932373
mean time: 1.9339712142944336
Pipeline stage StressChecker completed in 10.49s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.29s
chaiml-lexical-nemov8-1k1e5_v7 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-lexical-nemov8-1k1e5-v7-profiler
Waiting for inference service chaiml-lexical-nemov8-1k1e5-v7-profiler to be ready
Inference service chaiml-lexical-nemov8-1k1e5-v7-profiler ready after 130.31634640693665s
Pipeline stage MKMLProfilerDeployer completed in 130.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-lexical-nemov804581dc40801947872aba0fa9bbade9-deplokbmhp:/code/chaiverse_profiler_1725471804 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-lexical-nemov804581dc40801947872aba0fa9bbade9-deplokbmhp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725471804 && python profiles.py profile --best_of_n 4 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1725471804/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-lexical-nemov8-1k1e5-v7-profiler is running
Tearing down inference service chaiml-lexical-nemov8-1k1e5-v7-profiler
Service chaiml-lexical-nemov8-1k1e5-v7-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.05s
Shutdown handler unregistered and original handlers restored
chaiml-lexical-nemov8-1k1e5_v7 status is now inactive due to auto deactivation removed underperforming models
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-lexical-nemov8-1k1e5-v7-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.60s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-lexical-nemov8-1k1e5-v7-profiler
Waiting for inference service chaiml-lexical-nemov8-1k1e5-v7-profiler to be ready
Inference service chaiml-lexical-nemov8-1k1e5-v7-profiler ready after 150.34686183929443s
Pipeline stage MKMLProfilerDeployer completed in 150.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-lexical-nemov804581dc40801947872aba0fa9bbade9-deplo6q8w5:/code/chaiverse_profiler_1725485376 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-lexical-nemov804581dc40801947872aba0fa9bbade9-deplo6q8w5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725485376 && python profiles.py profile --best_of_n 4 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1725485376/summary.json'
kubectl exec -it chaiml-lexical-nemov804581dc40801947872aba0fa9bbade9-deplo6q8w5 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725485376/summary.json'
Pipeline stage MKMLProfilerRunner completed in 955.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-lexical-nemov8-1k1e5-v7-profiler is running
Tearing down inference service chaiml-lexical-nemov8-1k1e5-v7-profiler
Service chaiml-lexical-nemov8-1k1e5-v7-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.82s
Shutdown handler de-registered

Usage Metrics

Latency Metrics