developer_uid: bogoconic1
submission_id: meta-llama-llama-2-7b-chat-hf_v1
model_name: meta-llama-llama-2-7b-chat-hf_v1
model_group: meta-llama/Llama-2-7b-ch
status: torndown
timestamp: 2025-04-23T12:49:03+00:00
num_battles: 10712
num_wins: 3568
celo_rating: 1166.68
family_friendly_score: 0.6602
family_friendly_standard_error: 0.0066982976941906665
submission_type: basic
model_repo: meta-llama/Llama-2-7b-chat-hf
model_architecture: LlamaForCausalLM
model_num_parameters: 6738415616.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.8609741725750603, 'latency_mean': 1.1614026248455047, 'latency_p50': 1.1543186902999878, 'latency_p90': 1.2801241636276246}, {'batch_size': 3, 'throughput': 1.4181491188952715, 'latency_mean': 2.1099530065059664, 'latency_p50': 2.1134780645370483, 'latency_p90': 2.319503664970398}, {'batch_size': 5, 'throughput': 1.6483538357536027, 'latency_mean': 3.012834141254425, 'latency_p50': 3.012751817703247, 'latency_p90': 3.3659183502197267}, {'batch_size': 6, 'throughput': 1.7098470371190528, 'latency_mean': 3.4821925699710845, 'latency_p50': 3.508723020553589, 'latency_p90': 3.8667827606201173}, {'batch_size': 8, 'throughput': 1.7789112899396706, 'latency_mean': 4.464053997993469, 'latency_p50': 4.472928285598755, 'latency_p90': 5.031844544410705}, {'batch_size': 10, 'throughput': 1.8217046782346114, 'latency_mean': 5.449810780286789, 'latency_p50': 5.478163719177246, 'latency_p90': 6.1159227848052975}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: meta-llama-llama-2-7b-chat-hf_v1
is_internal_developer: True
language_model: meta-llama/Llama-2-7b-chat-hf
model_size: 7B
ranking_group: single
throughput_3p7s: 1.74
us_pacific_date: 2025-04-23
win_ratio: 0.3330843913368185
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
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}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name meta-llama-llama-2-7b-chat-hf-v1-mkmlizer
Waiting for job on meta-llama-llama-2-7b-chat-hf-v1-mkmlizer to finish
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ _____ __ __ ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ /___/ ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ Version: 0.12.8 ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ https://mk1.ai ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ The license key for the current software has been verified as ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ belonging to: ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ Chai Research Corp. ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ║ ║
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: Downloaded to shared memory in 29.851s
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_serxncy, device:0
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: quantized model in 16.389s
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: Processed model meta-llama/Llama-2-7b-chat-hf in 46.240s
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-llama-2-7b-chat-hf-v1
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-llama-2-7b-chat-hf-v1/config.json
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-llama-2-7b-chat-hf-v1/tokenizer_config.json
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-llama-2-7b-chat-hf-v1/special_tokens_map.json
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/meta-llama-llama-2-7b-chat-hf-v1/tokenizer.model
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-llama-2-7b-chat-hf-v1/tokenizer.json
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-llama-2-7b-chat-hf-v1/flywheel_model.0.safetensors
meta-llama-llama-2-7b-chat-hf-v1-mkmlizer: Loading 0: 0%| | 0/323 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/323 [00:00<00:09, 33.52it/s] Loading 0: 4%|▍ | 14/323 [00:00<00:05, 60.37it/s] Loading 0: 7%|▋ | 21/323 [00:00<00:05, 56.69it/s] Loading 0: 8%|▊ | 27/323 [00:00<00:05, 54.96it/s] Loading 0: 11%|█ | 35/323 [00:00<00:05, 53.46it/s] Loading 0: 14%|█▎ | 44/323 [00:00<00:04, 62.05it/s] Loading 0: 16%|█▌ | 51/323 [00:00<00:04, 58.08it/s] Loading 0: 18%|█▊ | 57/323 [00:01<00:04, 58.40it/s] Loading 0: 20%|██ | 65/323 [00:01<00:04, 55.08it/s] Loading 0: 23%|██▎ | 74/323 [00:01<00:04, 61.62it/s] Loading 0: 25%|██▌ | 81/323 [00:01<00:04, 56.98it/s] Loading 0: 27%|██▋ | 88/323 [00:01<00:03, 59.82it/s] Loading 0: 29%|██▉ | 95/323 [00:01<00:04, 55.38it/s] Loading 0: 32%|███▏ | 104/323 [00:01<00:03, 63.84it/s] Loading 0: 34%|███▍ | 111/323 [00:01<00:03, 59.74it/s] Loading 0: 37%|███▋ | 118/323 [00:02<00:03, 59.93it/s] Loading 0: 39%|███▊ | 125/323 [00:02<00:03, 50.85it/s] Loading 0: 41%|████▏ | 134/323 [00:02<00:03, 58.98it/s] Loading 0: 44%|████▎ | 141/323 [00:02<00:03, 53.79it/s] Loading 0: 46%|████▌ | 148/323 [00:02<00:03, 57.36it/s] Loading 0: 48%|████▊ | 155/323 [00:02<00:03, 53.42it/s] Loading 0: 51%|█████ | 165/323 [00:02<00:02, 56.60it/s] Loading 0: 54%|█████▍ | 175/323 [00:03<00:02, 58.75it/s] Loading 0: 57%|█████▋ | 184/323 [00:03<00:02, 65.75it/s] Loading 0: 59%|█████▉ | 191/323 [00:03<00:02, 61.56it/s] Loading 0: 61%|██████▏ | 198/323 [00:03<00:01, 63.37it/s] Loading 0: 63%|██████▎ | 205/323 [00:03<00:02, 56.55it/s] Loading 0: 66%|██████▋ | 214/323 [00:03<00:01, 64.37it/s] Loading 0: 68%|██████▊ | 221/323 [00:03<00:01, 60.99it/s] Loading 0: 71%|███████ | 228/323 [00:03<00:01, 62.89it/s] Loading 0: 73%|███████▎ | 235/323 [00:04<00:01, 56.56it/s] Loading 0: 75%|███████▍ | 242/323 [00:05<00:06, 12.07it/s] Loading 0: 76%|███████▋ | 247/323 [00:05<00:05, 14.38it/s] Loading 0: 79%|███████▉ | 256/323 [00:06<00:03, 19.78it/s] Loading 0: 82%|████████▏ | 265/323 [00:06<00:02, 27.06it/s] Loading 0: 84%|████████▍ | 272/323 [00:06<00:01, 31.35it/s] Loading 0: 86%|████████▋ | 279/323 [00:06<00:01, 37.16it/s] Loading 0: 89%|████████▊ | 286/323 [00:06<00:00, 39.40it/s] Loading 0: 91%|█████████▏| 295/323 [00:06<00:00, 48.73it/s] Loading 0: 93%|█████████▎| 302/323 [00:06<00:00, 50.02it/s] Loading 0: 96%|█████████▌| 309/323 [00:06<00:00, 54.20it/s] Loading 0: 98%|█████████▊| 316/323 [00:06<00:00, 51.58it/s]
Job meta-llama-llama-2-7b-chat-hf-v1-mkmlizer completed after 73.95s with status: succeeded
Stopping job with name meta-llama-llama-2-7b-chat-hf-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.56s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service meta-llama-llama-2-7b-chat-hf-v1
Waiting for inference service meta-llama-llama-2-7b-chat-hf-v1 to be ready
Inference service meta-llama-llama-2-7b-chat-hf-v1 ready after 140.5589988231659s
Pipeline stage MKMLDeployer completed in 141.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3755946159362793s
Received healthy response to inference request in 1.1589422225952148s
Received healthy response to inference request in 1.3194351196289062s
Received healthy response to inference request in 1.505126953125s
Received healthy response to inference request in 1.382401943206787s
5 requests
0 failed requests
5th percentile: 1.1910408020019532
10th percentile: 1.2231393814086915
20th percentile: 1.287336540222168
30th percentile: 1.3320284843444825
40th percentile: 1.3572152137756348
50th percentile: 1.382401943206787
60th percentile: 1.4314919471740724
70th percentile: 1.4805819511413574
80th percentile: 1.6792204856872561
90th percentile: 2.0274075508117675
95th percentile: 2.201501083374023
99th percentile: 2.340775909423828
mean time: 1.5483001708984374
Pipeline stage StressChecker completed in 9.74s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.88s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.93s
Shutdown handler de-registered
meta-llama-llama-2-7b-chat-hf_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service meta-llama-llama-2-7b-chat-hf-v1-profiler
Waiting for inference service meta-llama-llama-2-7b-chat-hf-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4108.55s
Shutdown handler de-registered
meta-llama-llama-2-7b-chat-hf_v1 status is now inactive due to auto deactivation removed underperforming models
meta-llama-llama-2-7b-chat-hf_v1 status is now torndown due to DeploymentManager action