submission_id: inv-konstanta-v4-alpha-7b_v6
developer_uid: zonemercy
status: inactive
model_repo: Inv/Konstanta-V4-Alpha-7B
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "Role-play as {bot_name} based on Persona: {memory}. Avoid repetition, don't loop. Develop the plot slowly, always stay in character. Describe all actions in full, elaborate, explicit, graphic, and vivid detail. Mention all relevant sensory perceptions.", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:'}
timestamp: 2024-03-27T18:49:19+00:00
model_name: inv-konstanta-v4-alpha-7b_v6
model_eval_status: success
safety_score: 0.98
entertaining: 7.12
stay_in_character: 8.51
user_preference: 7.52
double_thumbs_up: 799
thumbs_up: 1063
thumbs_down: 433
num_battles: 111897
num_wins: 60386
win_ratio: 0.5396570059965862
celo_rating: 1185.79
Resubmit model
Running pipeline stage MKMLizer
Starting job with name inv-konstanta-v4-alpha-7b-v6-mkmlizer
Waiting for job on inv-konstanta-v4-alpha-7b-v6-mkmlizer to finish
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ _____ __ __ ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ /___/ ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ Version: 0.6.11 ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ The license key for the current software has been verified as ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ belonging to: ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ Chai Research Corp. ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ║ ║
inv-konstanta-v4-alpha-7b-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
inv-konstanta-v4-alpha-7b-v6-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.0MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: README.md: 0%| | 0.00/1.31k [00:00<?, ?B/s] README.md: 100%|██████████| 1.31k/1.31k [00:00<00:00, 17.1MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: config.json: 0%| | 0.00/632 [00:00<?, ?B/s] config.json: 100%|██████████| 632/632 [00:00<00:00, 8.84MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: mergekit_config.yml: 0%| | 0.00/410 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 410/410 [00:00<00:00, 5.42MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: model-00001-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00001-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<00:31, 62.3MB/s] model-00001-of-00008.safetensors: 1%| | 21.0M/1.98G [00:00<00:36, 54.0MB/s] model-00001-of-00008.safetensors: 2%|▏ | 41.9M/1.98G [00:00<00:19, 101MB/s] model-00001-of-00008.safetensors: 4%|▍ | 83.9M/1.98G [00:00<00:09, 192MB/s] model-00001-of-00008.safetensors: 6%|▌ | 115M/1.98G [00:00<00:09, 199MB/s] model-00001-of-00008.safetensors: 10%|▉ | 189M/1.98G [00:00<00:05, 317MB/s] model-00001-of-00008.safetensors: 15%|█▍ | 294M/1.98G [00:00<00:03, 504MB/s] model-00001-of-00008.safetensors: 19%|█▉ | 377M/1.98G [00:01<00:02, 585MB/s] model-00001-of-00008.safetensors: 23%|██▎ | 451M/1.98G [00:01<00:02, 540MB/s] model-00001-of-00008.safetensors: 26%|██▋ | 524M/1.98G [00:01<00:02, 580MB/s] model-00001-of-00008.safetensors: 30%|██▉ | 587M/1.98G [00:01<00:02, 566MB/s] model-00001-of-00008.safetensors: 33%|███▎ | 650M/1.98G [00:01<00:02, 576MB/s] model-00001-of-00008.safetensors: 39%|███▊ | 765M/1.98G [00:01<00:01, 645MB/s] model-00001-of-00008.safetensors: 42%|████▏ | 839M/1.98G [00:01<00:01, 603MB/s] model-00001-of-00008.safetensors: 46%|████▌ | 902M/1.98G [00:01<00:01, 598MB/s] model-00001-of-00008.safetensors: 49%|████▊ | 965M/1.98G [00:02<00:01, 554MB/s] model-00001-of-00008.safetensors: 53%|█████▎ | 1.06G/1.98G [00:02<00:01, 645MB/s] model-00001-of-00008.safetensors: 58%|█████▊ | 1.14G/1.98G [00:02<00:01, 695MB/s] model-00001-of-00008.safetensors: 61%|██████▏ | 1.22G/1.98G [00:02<00:01, 664MB/s] model-00001-of-00008.safetensors: 67%|██████▋ | 1.32G/1.98G [00:02<00:00, 746MB/s] model-00001-of-00008.safetensors: 71%|███████ | 1.40G/1.98G [00:02<00:00, 753MB/s] model-00001-of-00008.safetensors: 77%|███████▋ | 1.52G/1.98G [00:02<00:00, 860MB/s] model-00001-of-00008.safetensors: 86%|████████▌ | 1.70G/1.98G [00:02<00:00, 1.11GB/s] model-00001-of-00008.safetensors: 97%|█████████▋| 1.92G/1.98G [00:02<00:00, 1.41GB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:05<00:00, 380MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: model-00002-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00002-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<01:34, 20.4MB/s] model-00002-of-00008.safetensors: 2%|▏ | 41.9M/1.95G [00:00<00:24, 77.4MB/s] model-00002-of-00008.safetensors: 5%|▍ | 94.4M/1.95G [00:00<00:10, 170MB/s] model-00002-of-00008.safetensors: 8%|▊ | 157M/1.95G [00:00<00:06, 265MB/s] model-00002-of-00008.safetensors: 15%|█▍ | 283M/1.95G [00:01<00:03, 461MB/s] model-00002-of-00008.safetensors: 19%|█▉ | 377M/1.95G [00:01<00:03, 521MB/s] model-00002-of-00008.safetensors: 27%|██▋ | 535M/1.95G [00:01<00:01, 769MB/s] model-00002-of-00008.safetensors: 35%|███▌ | 682M/1.95G [00:01<00:01, 888MB/s] model-00002-of-00008.safetensors: 40%|████ | 786M/1.95G [00:01<00:01, 920MB/s] model-00002-of-00008.safetensors: 46%|████▌ | 891M/1.95G [00:01<00:01, 859MB/s] model-00002-of-00008.safetensors: 53%|█████▎ | 1.04G/1.95G [00:01<00:00, 997MB/s] model-00002-of-00008.safetensors: 61%|██████ | 1.19G/1.95G [00:01<00:00, 1.13GB/s] model-00002-of-00008.safetensors: 70%|███████ | 1.37G/1.95G [00:01<00:00, 1.29GB/s] model-00002-of-00008.safetensors: 79%|███████▉ | 1.54G/1.95G [00:02<00:00, 1.40GB/s] model-00002-of-00008.safetensors: 91%|█████████▏| 1.78G/1.95G [00:02<00:00, 1.67GB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:02<00:00, 721MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: model-00003-of-00008.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00003-of-00008.safetensors: 1%| | 10.5M/1.98G [00:00<01:27, 22.5MB/s] model-00003-of-00008.safetensors: 3%|▎ | 62.9M/1.98G [00:00<00:15, 124MB/s] model-00003-of-00008.safetensors: 6%|▌ | 115M/1.98G [00:00<00:08, 210MB/s] model-00003-of-00008.safetensors: 9%|▉ | 178M/1.98G [00:00<00:05, 301MB/s] model-00003-of-00008.safetensors: 15%|█▌ | 304M/1.98G [00:00<00:03, 537MB/s] model-00003-of-00008.safetensors: 19%|█▉ | 377M/1.98G [00:01<00:02, 583MB/s] model-00003-of-00008.safetensors: 25%|██▍ | 493M/1.98G [00:01<00:02, 622MB/s] model-00003-of-00008.safetensors: 29%|██▊ | 566M/1.98G [00:01<00:02, 584MB/s] model-00003-of-00008.safetensors: 37%|███▋ | 724M/1.98G [00:01<00:01, 803MB/s] model-00003-of-00008.safetensors: 41%|████▏ | 818M/1.98G [00:01<00:01, 807MB/s] model-00003-of-00008.safetensors: 47%|████▋ | 933M/1.98G [00:01<00:01, 797MB/s] model-00003-of-00008.safetensors: 55%|█████▍ | 1.09G/1.98G [00:01<00:00, 976MB/s] model-00003-of-00008.safetensors: 60%|██████ | 1.19G/1.98G [00:01<00:00, 988MB/s] model-00003-of-00008.safetensors: 73%|███████▎ | 1.45G/1.98G [00:02<00:00, 1.38GB/s] model-00003-of-00008.safetensors: 82%|████████▏ | 1.62G/1.98G [00:02<00:00, 1.41GB/s] model-00003-of-00008.safetensors: 89%|████████▉ | 1.77G/1.98G [00:02<00:00, 1.27GB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:02<00:00, 813MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: model-00004-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00004-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<01:31, 21.2MB/s] model-00004-of-00008.safetensors: 5%|▍ | 94.4M/1.95G [00:00<00:09, 204MB/s] model-00004-of-00008.safetensors: 16%|█▌ | 304M/1.95G [00:00<00:02, 662MB/s] model-00004-of-00008.safetensors: 25%|██▍ | 482M/1.95G [00:00<00:01, 935MB/s] model-00004-of-00008.safetensors: 32%|███▏ | 629M/1.95G [00:01<00:01, 661MB/s] model-00004-of-00008.safetensors: 38%|███▊ | 744M/1.95G [00:01<00:01, 691MB/s] model-00004-of-00008.safetensors: 44%|████▎ | 849M/1.95G [00:01<00:01, 676MB/s] model-00004-of-00008.safetensors: 48%|████▊ | 940M/1.95G [00:01<00:01, 583MB/s] model-00004-of-00008.safetensors: 54%|█████▎ | 1.04G/1.95G [00:01<00:01, 665MB/s] model-00004-of-00008.safetensors: 58%|█████▊ | 1.13G/1.95G [00:01<00:01, 656MB/s] model-00004-of-00008.safetensors: 62%|██████▏ | 1.21G/1.95G [00:02<00:01, 676MB/s] model-00004-of-00008.safetensors: 67%|██████▋ | 1.30G/1.95G [00:02<00:01, 601MB/s] model-00004-of-00008.safetensors: 73%|███████▎ | 1.41G/1.95G [00:02<00:00, 721MB/s] model-00004-of-00008.safetensors: 82%|████████▏ | 1.60G/1.95G [00:02<00:00, 967MB/s] model-00004-of-00008.safetensors: 96%|█████████▌| 1.86G/1.95G [00:02<00:00, 1.38GB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 473MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: model-00005-of-00008.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00005-of-00008.safetensors: 1%| | 10.5M/1.89G [00:00<01:11, 26.2MB/s] model-00005-of-00008.safetensors: 1%| | 21.0M/1.89G [00:00<00:43, 42.8MB/s] model-00005-of-00008.safetensors: 7%|▋ | 126M/1.89G [00:00<00:06, 291MB/s] model-00005-of-00008.safetensors: 10%|▉ | 189M/1.89G [00:00<00:04, 377MB/s] model-00005-of-00008.safetensors: 17%|█▋ | 315M/1.89G [00:00<00:02, 599MB/s] model-00005-of-00008.safetensors: 22%|██▏ | 409M/1.89G [00:00<00:02, 652MB/s] model-00005-of-00008.safetensors: 27%|██▋ | 514M/1.89G [00:01<00:01, 750MB/s] model-00005-of-00008.safetensors: 34%|███▍ | 640M/1.89G [00:01<00:01, 873MB/s] model-00005-of-00008.safetensors: 39%|███▉ | 734M/1.89G [00:01<00:01, 873MB/s] model-00005-of-00008.safetensors: 44%|████▍ | 828M/1.89G [00:01<00:01, 886MB/s] model-00005-of-00008.safetensors: 49%|████▉ | 923M/1.89G [00:01<00:01, 897MB/s] model-00005-of-00008.safetensors: 60%|█████▉ | 1.13G/1.89G [00:01<00:00, 1.23GB/s] model-00005-of-00008.safetensors: 71%|███████ | 1.34G/1.89G [00:01<00:00, 1.47GB/s] model-00005-of-00008.safetensors: 82%|████████▏ | 1.54G/1.89G [00:01<00:00, 1.61GB/s] model-00005-of-00008.safetensors: 97%|█████████▋| 1.84G/1.89G [00:01<00:00, 1.93GB/s] model-00005-of-00008.safetensors: 100%|█████████▉| 1.89G/1.89G [00:06<00:00, 309MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: model-00006-of-00008.safetensors: 0%| | 0.00/1.92G [00:00<?, ?B/s] model-00006-of-00008.safetensors: 1%| | 10.5M/1.92G [00:00<01:10, 27.3MB/s] model-00006-of-00008.safetensors: 4%|▍ | 73.4M/1.92G [00:00<00:11, 161MB/s] model-00006-of-00008.safetensors: 5%|▌ | 105M/1.92G [00:00<00:09, 191MB/s] model-00006-of-00008.safetensors: 9%|▉ | 178M/1.92G [00:00<00:05, 302MB/s] model-00006-of-00008.safetensors: 11%|█▏ | 220M/1.92G [00:00<00:05, 312MB/s] model-00006-of-00008.safetensors: 14%|█▍ | 273M/1.92G [00:01<00:05, 329MB/s] model-00006-of-00008.safetensors: 16%|█▋ | 315M/1.92G [00:01<00:04, 332MB/s] model-00006-of-00008.safetensors: 20%|██ | 388M/1.92G [00:01<00:03, 426MB/s] model-00006-of-00008.safetensors: 24%|██▍ | 461M/1.92G [00:01<00:03, 485MB/s] model-00006-of-00008.safetensors: 28%|██▊ | 535M/1.92G [00:01<00:02, 546MB/s] model-00006-of-00008.safetensors: 31%|███ | 598M/1.92G [00:01<00:03, 426MB/s] model-00006-of-00008.safetensors: 35%|███▍ | 671M/1.92G [00:01<00:02, 491MB/s] model-00006-of-00008.safetensors: 38%|███▊ | 734M/1.92G [00:01<00:02, 471MB/s] model-00006-of-00008.safetensors: 43%|████▎ | 828M/1.92G [00:02<00:01, 549MB/s] model-00006-of-00008.safetensors: 47%|████▋ | 902M/1.92G [00:02<00:01, 546MB/s] model-00006-of-00008.safetensors: 52%|█████▏ | 996M/1.92G [00:02<00:01, 598MB/s] model-00006-of-00008.safetensors: 58%|█████▊ | 1.12G/1.92G [00:02<00:01, 740MB/s] model-00006-of-00008.safetensors: 62%|██████▏ | 1.20G/1.92G [00:02<00:00, 763MB/s] model-00006-of-00008.safetensors: 67%|██████▋ | 1.29G/1.92G [00:02<00:00, 786MB/s] model-00006-of-00008.safetensors: 72%|███████▏ | 1.39G/1.92G [00:02<00:00, 826MB/s] model-00006-of-00008.safetensors: 79%|███████▊ | 1.51G/1.92G [00:02<00:00, 944MB/s] model-00006-of-00008.safetensors: 90%|████████▉ | 1.72G/1.92G [00:03<00:00, 1.26GB/s] model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:03<00:00, 615MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: model-00007-of-00008.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00007-of-00008.safetensors: 1%| | 10.5M/1.95G [00:00<01:11, 27.1MB/s] model-00007-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:00<00:10, 170MB/s] model-00007-of-00008.safetensors: 6%|▌ | 115M/1.95G [00:00<00:09, 193MB/s] model-00007-of-00008.safetensors: 9%|▊ | 168M/1.95G [00:00<00:06, 255MB/s] model-00007-of-00008.safetensors: 10%|█ | 199M/1.95G [00:01<00:07, 228MB/s] model-00007-of-00008.safetensors: 13%|█▎ | 252M/1.95G [00:01<00:05, 284MB/s] model-00007-of-00008.safetensors: 15%|█▌ | 294M/1.95G [00:01<00:05, 295MB/s] model-00007-of-00008.safetensors: 18%|█▊ | 346M/1.95G [00:01<00:05, 315MB/s] model-00007-of-00008.safetensors: 21%|██ | 409M/1.95G [00:01<00:04, 372MB/s] model-00007-of-00008.safetensors: 25%|██▍ | 482M/1.95G [00:01<00:03, 433MB/s] model-00007-of-00008.safetensors: 29%|██▉ | 566M/1.95G [00:01<00:02, 511MB/s] model-00007-of-00008.safetensors: 33%|███▎ | 650M/1.95G [00:01<00:02, 590MB/s] model-00007-of-00008.safetensors: 38%|███▊ | 734M/1.95G [00:01<00:01, 641MB/s] model-00007-of-00008.safetensors: 41%|████▏ | 807M/1.95G [00:02<00:01, 656MB/s] model-00007-of-00008.safetensors: 47%|████▋ | 912M/1.95G [00:02<00:01, 718MB/s] model-00007-of-00008.safetensors: 51%|█████ | 992M/1.95G [00:02<00:01, 739MB/s] model-00007-of-00008.safetensors: 57%|█████▋ | 1.12G/1.95G [00:02<00:00, 851MB/s] model-00007-of-00008.safetensors: 63%|██████▎ | 1.22G/1.95G [00:02<00:00, 781MB/s] model-00007-of-00008.safetensors: 69%|██████▉ | 1.35G/1.95G [00:02<00:00, 886MB/s] model-00007-of-00008.safetensors: 77%|███████▋ | 1.51G/1.95G [00:02<00:00, 1.05GB/s] model-00007-of-00008.safetensors: 87%|████████▋ | 1.69G/1.95G [00:02<00:00, 1.26GB/s] model-00007-of-00008.safetensors: 94%|█████████▍| 1.83G/1.95G [00:03<00:00, 1.29GB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:03<00:00, 601MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/872M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 1%| | 10.5M/872M [00:00<00:19, 43.6MB/s] model-00008-of-00008.safetensors: 7%|▋ | 62.9M/872M [00:00<00:03, 213MB/s] model-00008-of-00008.safetensors: 12%|█▏ | 105M/872M [00:00<00:04, 175MB/s] model-00008-of-00008.safetensors: 18%|█▊ | 157M/872M [00:00<00:02, 249MB/s] model-00008-of-00008.safetensors: 28%|██▊ | 243M/872M [00:00<00:01, 394MB/s] model-00008-of-00008.safetensors: 47%|████▋ | 411M/872M [00:00<00:00, 720MB/s] model-00008-of-00008.safetensors: 60%|██████ | 526M/872M [00:01<00:00, 827MB/s] model-00008-of-00008.safetensors: 72%|███████▏ | 631M/872M [00:01<00:00, 841MB/s] model-00008-of-00008.safetensors: 95%|█████████▌| 831M/872M [00:01<00:00, 1.15GB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:01<00:00, 638MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: model.safetensors.index.json: 0%| | 0.00/22.8k [00:00<?, ?B/s] model.safetensors.index.json: 100%|██████████| 22.8k/22.8k [00:00<00:00, 139MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 3.49MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 15.4MB/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 15.3MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 50.2MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: tokenizer_config.json: 0%| | 0.00/967 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 8.02MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: Downloaded to shared memory in 32.658s
inv-konstanta-v4-alpha-7b-v6-mkmlizer: quantizing model to /dev/shm/model_cache
inv-konstanta-v4-alpha-7b-v6-mkmlizer: Saving mkml model at /dev/shm/model_cache
inv-konstanta-v4-alpha-7b-v6-mkmlizer: Reading /tmp/tmpz0u7075x/model.safetensors.index.json
inv-konstanta-v4-alpha-7b-v6-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<00:42, 6.90it/s] Profiling: 4%|▍ | 12/291 [00:00<00:04, 56.05it/s] Profiling: 10%|▉ | 29/291 [00:00<00:02, 101.82it/s] Profiling: 14%|█▍ | 41/291 [00:00<00:03, 82.97it/s] Profiling: 20%|█▉ | 57/291 [00:00<00:02, 104.68it/s] Profiling: 25%|██▌ | 74/291 [00:00<00:01, 122.87it/s] Profiling: 30%|███ | 88/291 [00:00<00:01, 108.27it/s] Profiling: 34%|███▍ | 100/291 [00:01<00:01, 109.81it/s] Profiling: 40%|████ | 117/291 [00:01<00:01, 125.21it/s] Profiling: 45%|████▌ | 131/291 [00:01<00:01, 103.29it/s] Profiling: 50%|█████ | 146/291 [00:01<00:01, 113.98it/s] Profiling: 55%|█████▍ | 160/291 [00:02<00:04, 27.87it/s] Profiling: 59%|█████▉ | 173/291 [00:02<00:03, 35.46it/s] Profiling: 67%|██████▋ | 195/291 [00:03<00:01, 53.04it/s] Profiling: 71%|███████▏ | 208/291 [00:04<00:03, 25.09it/s] Profiling: 77%|███████▋ | 225/291 [00:04<00:01, 34.58it/s] Profiling: 81%|████████▏ | 237/291 [00:04<00:01, 39.99it/s] Profiling: 87%|████████▋ | 252/291 [00:04<00:00, 51.11it/s] Profiling: 94%|█████████▍| 274/291 [00:04<00:00, 66.12it/s] Profiling: 98%|█████████▊| 286/291 [00:05<00:00, 72.31it/s] Profiling: 100%|██████████| 291/291 [00:05<00:00, 57.44it/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: quantized model in 15.889s
inv-konstanta-v4-alpha-7b-v6-mkmlizer: Processed model Inv/Konstanta-V4-Alpha-7B in 49.456s
inv-konstanta-v4-alpha-7b-v6-mkmlizer: creating bucket guanaco-mkml-models
inv-konstanta-v4-alpha-7b-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
inv-konstanta-v4-alpha-7b-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v6
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v6/special_tokens_map.json
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v6/tokenizer_config.json
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v6/tokenizer.model
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v6/config.json
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v6/tokenizer.json
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/inv-konstanta-v4-alpha-7b-v6/mkml_model.tensors
inv-konstanta-v4-alpha-7b-v6-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
inv-konstanta-v4-alpha-7b-v6-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:1067: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
inv-konstanta-v4-alpha-7b-v6-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v6-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 11.7MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:690: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
inv-konstanta-v4-alpha-7b-v6-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v6-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.48MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 11.0MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 24.6MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:472: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
inv-konstanta-v4-alpha-7b-v6-mkmlizer: warnings.warn(
inv-konstanta-v4-alpha-7b-v6-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%| | 10.5M/1.44G [00:00<00:19, 74.9MB/s] pytorch_model.bin: 2%|▏ | 31.5M/1.44G [00:00<00:21, 65.8MB/s] pytorch_model.bin: 10%|█ | 147M/1.44G [00:00<00:04, 298MB/s] pytorch_model.bin: 13%|█▎ | 189M/1.44G [00:00<00:03, 327MB/s] pytorch_model.bin: 16%|█▌ | 231M/1.44G [00:00<00:03, 350MB/s] pytorch_model.bin: 20%|██ | 294M/1.44G [00:00<00:02, 406MB/s] pytorch_model.bin: 25%|██▌ | 367M/1.44G [00:01<00:02, 478MB/s] pytorch_model.bin: 29%|██▉ | 419M/1.44G [00:01<00:02, 456MB/s] pytorch_model.bin: 34%|███▍ | 490M/1.44G [00:01<00:01, 521MB/s] pytorch_model.bin: 42%|████▏ | 606M/1.44G [00:01<00:01, 691MB/s] pytorch_model.bin: 54%|█████▎ | 773M/1.44G [00:01<00:00, 947MB/s] pytorch_model.bin: 61%|██████ | 878M/1.44G [00:01<00:00, 785MB/s] pytorch_model.bin: 71%|███████ | 1.03G/1.44G [00:01<00:00, 882MB/s] pytorch_model.bin: 85%|████████▌ | 1.23G/1.44G [00:01<00:00, 1.15GB/s] pytorch_model.bin: 99%|█████████▊| 1.42G/1.44G [00:02<00:00, 1.11GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:03<00:00, 399MB/s]
inv-konstanta-v4-alpha-7b-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
inv-konstanta-v4-alpha-7b-v6-mkmlizer: Saving duration: 0.230s
inv-konstanta-v4-alpha-7b-v6-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 7.239s
inv-konstanta-v4-alpha-7b-v6-mkmlizer: creating bucket guanaco-reward-models
inv-konstanta-v4-alpha-7b-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
inv-konstanta-v4-alpha-7b-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v6_reward
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v6_reward/special_tokens_map.json
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v6_reward/tokenizer_config.json
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v6_reward/merges.txt
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v6_reward/config.json
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v6_reward/vocab.json
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v6_reward/tokenizer.json
inv-konstanta-v4-alpha-7b-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/inv-konstanta-v4-alpha-7b-v6_reward/reward.tensors
Job inv-konstanta-v4-alpha-7b-v6-mkmlizer completed after 74.63s with status: succeeded
Stopping job with name inv-konstanta-v4-alpha-7b-v6-mkmlizer
Pipeline stage MKMLizer completed in 79.20s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service inv-konstanta-v4-alpha-7b-v6
Waiting for inference service inv-konstanta-v4-alpha-7b-v6 to be ready
Inference service inv-konstanta-v4-alpha-7b-v6 ready after 40.265300035476685s
Pipeline stage ISVCDeployer completed in 47.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7163543701171875s
Received healthy response to inference request in 1.175769329071045s
Received healthy response to inference request in 1.1687073707580566s
Received healthy response to inference request in 1.1802124977111816s
Received healthy response to inference request in 1.186631679534912s
5 requests
0 failed requests
5th percentile: 1.1701197624206543
10th percentile: 1.171532154083252
20th percentile: 1.1743569374084473
30th percentile: 1.1766579627990723
40th percentile: 1.1784352302551269
50th percentile: 1.1802124977111816
60th percentile: 1.1827801704406737
70th percentile: 1.185347843170166
80th percentile: 1.2925762176513673
90th percentile: 1.5044652938842773
95th percentile: 1.6104098320007323
99th percentile: 1.6951654624938965
mean time: 1.2855350494384765
Pipeline stage StressChecker completed in 7.35s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.06s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.06s
M-Eval Dataset for topic stay_in_character is loaded
inv-konstanta-v4-alpha-7b_v6 status is now deployed due to DeploymentManager action
inv-konstanta-v4-alpha-7b_v6 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics