submission_id: saishf-kuro-lotus-10-7b_v3
developer_uid: chai_backend_admin
status: inactive
model_repo: saishf/Kuro-Lotus-10.7B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'top_k': 50, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, '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}:'}
reward_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}:'}
timestamp: 2024-04-02T17:46:34+00:00
model_name: auto_submit_ricum_kajejiwuho
model_eval_status: success
safety_score: 0.71
entertaining: 6.68
stay_in_character: 8.35
user_preference: 7.22
double_thumbs_up: 233
thumbs_up: 382
thumbs_down: 280
num_battles: 23563
num_wins: 9943
win_ratio: 0.42197513050120955
celo_rating: 1099.0
Resubmit model
Running pipeline stage MKMLizer
Starting job with name saishf-kuro-lotus-10-7b-v3-mkmlizer
Waiting for job on saishf-kuro-lotus-10-7b-v3-mkmlizer to finish
saishf-kuro-lotus-10-7b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ _____ __ __ ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ /___/ ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ Version: 0.6.11 ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ The license key for the current software has been verified as ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ belonging to: ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ Chai Research Corp. ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ║ ║
saishf-kuro-lotus-10-7b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
saishf-kuro-lotus-10-7b-v3-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 8.03MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: README.md: 0%| | 0.00/4.30k [00:00<?, ?B/s] README.md: 100%|██████████| 4.30k/4.30k [00:00<00:00, 21.4MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: config.json: 0%| | 0.00/704 [00:00<?, ?B/s] config.json: 100%|██████████| 704/704 [00:00<00:00, 4.18MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: mergekit_config.yml: 0%| | 0.00/384 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 384/384 [00:00<00:00, 2.86MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00001-of-00011.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00001-of-00011.safetensors: 1%| | 10.5M/1.89G [00:00<02:02, 15.3MB/s] model-00001-of-00011.safetensors: 1%| | 21.0M/1.89G [00:00<01:01, 30.2MB/s] model-00001-of-00011.safetensors: 2%|▏ | 31.5M/1.89G [00:01<01:54, 16.3MB/s] model-00001-of-00011.safetensors: 4%|▍ | 83.9M/1.89G [00:01<00:28, 62.5MB/s] model-00001-of-00011.safetensors: 7%|▋ | 136M/1.89G [00:02<00:20, 86.9MB/s] model-00001-of-00011.safetensors: 10%|▉ | 189M/1.89G [00:02<00:13, 126MB/s] model-00001-of-00011.safetensors: 12%|█▏ | 231M/1.89G [00:02<00:10, 160MB/s] model-00001-of-00011.safetensors: 14%|█▍ | 262M/1.89G [00:02<00:09, 167MB/s] model-00001-of-00011.safetensors: 17%|█▋ | 315M/1.89G [00:02<00:07, 221MB/s] model-00001-of-00011.safetensors: 24%|██▍ | 451M/1.89G [00:02<00:03, 428MB/s] model-00001-of-00011.safetensors: 30%|██▉ | 566M/1.89G [00:03<00:02, 576MB/s] model-00001-of-00011.safetensors: 34%|███▍ | 650M/1.89G [00:03<00:02, 545MB/s] model-00001-of-00011.safetensors: 38%|███▊ | 724M/1.89G [00:03<00:02, 583MB/s] model-00001-of-00011.safetensors: 67%|██████▋ | 1.27G/1.89G [00:03<00:00, 1.73GB/s] model-00001-of-00011.safetensors: 78%|███████▊ | 1.48G/1.89G [00:03<00:00, 962MB/s] model-00001-of-00011.safetensors: 87%|████████▋ | 1.65G/1.89G [00:04<00:00, 957MB/s] model-00001-of-00011.safetensors: 95%|█████████▌| 1.80G/1.89G [00:04<00:00, 929MB/s] model-00001-of-00011.safetensors: 100%|█████████▉| 1.89G/1.89G [00:04<00:00, 436MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00002-of-00011.safetensors: 0%| | 0.00/1.99G [00:00<?, ?B/s] model-00002-of-00011.safetensors: 1%| | 10.5M/1.99G [00:00<01:48, 18.3MB/s] model-00002-of-00011.safetensors: 1%| | 21.0M/1.99G [00:00<01:03, 30.9MB/s] model-00002-of-00011.safetensors: 2%|▏ | 31.5M/1.99G [00:01<01:19, 24.6MB/s] model-00002-of-00011.safetensors: 5%|▌ | 105M/1.99G [00:01<00:15, 118MB/s] model-00002-of-00011.safetensors: 8%|▊ | 157M/1.99G [00:01<00:10, 182MB/s] model-00002-of-00011.safetensors: 10%|█ | 199M/1.99G [00:01<00:10, 175MB/s] model-00002-of-00011.safetensors: 12%|█▏ | 231M/1.99G [00:01<00:08, 196MB/s] model-00002-of-00011.safetensors: 14%|█▍ | 283M/1.99G [00:01<00:06, 247MB/s] model-00002-of-00011.safetensors: 16%|█▋ | 325M/1.99G [00:02<00:06, 249MB/s] model-00002-of-00011.safetensors: 18%|█▊ | 367M/1.99G [00:02<00:05, 284MB/s] model-00002-of-00011.safetensors: 21%|██ | 409M/1.99G [00:02<00:05, 295MB/s] model-00002-of-00011.safetensors: 26%|██▌ | 514M/1.99G [00:02<00:03, 469MB/s] model-00002-of-00011.safetensors: 32%|███▏ | 629M/1.99G [00:02<00:02, 623MB/s] model-00002-of-00011.safetensors: 35%|███▌ | 703M/1.99G [00:02<00:02, 514MB/s] model-00002-of-00011.safetensors: 44%|████▍ | 870M/1.99G [00:02<00:01, 768MB/s] model-00002-of-00011.safetensors: 69%|██████▊ | 1.36G/1.99G [00:03<00:00, 1.74GB/s] model-00002-of-00011.safetensors: 82%|████████▏ | 1.63G/1.99G [00:03<00:00, 1.93GB/s] model-00002-of-00011.safetensors: 93%|█████████▎| 1.85G/1.99G [00:03<00:00, 1.25GB/s] model-00002-of-00011.safetensors: 100%|█████████▉| 1.99G/1.99G [00:04<00:00, 481MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00003-of-00011.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00003-of-00011.safetensors: 1%| | 10.5M/1.98G [00:00<01:13, 26.7MB/s] model-00003-of-00011.safetensors: 1%| | 21.0M/1.98G [00:01<01:50, 17.8MB/s] model-00003-of-00011.safetensors: 2%|▏ | 41.9M/1.98G [00:01<00:59, 32.6MB/s] model-00003-of-00011.safetensors: 3%|▎ | 52.4M/1.98G [00:01<00:53, 35.8MB/s] model-00003-of-00011.safetensors: 4%|▍ | 83.9M/1.98G [00:01<00:26, 72.1MB/s] model-00003-of-00011.safetensors: 11%|█ | 210M/1.98G [00:01<00:07, 229MB/s] model-00003-of-00011.safetensors: 13%|█▎ | 252M/1.98G [00:02<00:08, 202MB/s] model-00003-of-00011.safetensors: 16%|█▋ | 325M/1.98G [00:02<00:06, 273MB/s] model-00003-of-00011.safetensors: 21%|██ | 419M/1.98G [00:02<00:04, 387MB/s] model-00003-of-00011.safetensors: 26%|██▋ | 524M/1.98G [00:02<00:02, 506MB/s] model-00003-of-00011.safetensors: 33%|███▎ | 650M/1.98G [00:02<00:02, 645MB/s] model-00003-of-00011.safetensors: 37%|███▋ | 734M/1.98G [00:02<00:02, 608MB/s] model-00003-of-00011.safetensors: 43%|████▎ | 860M/1.98G [00:02<00:01, 751MB/s] model-00003-of-00011.safetensors: 72%|███████▏ | 1.42G/1.98G [00:03<00:00, 1.89GB/s] model-00003-of-00011.safetensors: 83%|████████▎ | 1.65G/1.98G [00:03<00:00, 1.22GB/s] model-00003-of-00011.safetensors: 92%|█████████▏| 1.82G/1.98G [00:03<00:00, 1.25GB/s] model-00003-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:03<00:00, 501MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00004-of-00011.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00004-of-00011.safetensors: 1%| | 10.5M/1.95G [00:00<01:12, 26.8MB/s] model-00004-of-00011.safetensors: 2%|▏ | 31.5M/1.95G [00:00<00:29, 65.5MB/s] model-00004-of-00011.safetensors: 2%|▏ | 41.9M/1.95G [00:01<00:54, 35.1MB/s] model-00004-of-00011.safetensors: 4%|▍ | 83.9M/1.95G [00:01<00:28, 66.1MB/s] model-00004-of-00011.safetensors: 5%|▌ | 105M/1.95G [00:01<00:22, 80.3MB/s] model-00004-of-00011.safetensors: 8%|▊ | 147M/1.95G [00:01<00:13, 129MB/s] model-00004-of-00011.safetensors: 10%|█ | 199M/1.95G [00:01<00:10, 160MB/s] model-00004-of-00011.safetensors: 11%|█▏ | 220M/1.95G [00:02<00:10, 164MB/s] model-00004-of-00011.safetensors: 13%|█▎ | 252M/1.95G [00:02<00:09, 188MB/s] model-00004-of-00011.safetensors: 16%|█▌ | 304M/1.95G [00:02<00:06, 249MB/s] model-00004-of-00011.safetensors: 17%|█▋ | 336M/1.95G [00:02<00:06, 260MB/s] model-00004-of-00011.safetensors: 19%|█▉ | 367M/1.95G [00:02<00:07, 218MB/s] model-00004-of-00011.safetensors: 23%|██▎ | 440M/1.95G [00:02<00:04, 305MB/s] model-00004-of-00011.safetensors: 26%|██▋ | 514M/1.95G [00:02<00:03, 398MB/s] model-00004-of-00011.safetensors: 31%|███ | 598M/1.95G [00:02<00:02, 489MB/s] model-00004-of-00011.safetensors: 37%|███▋ | 724M/1.95G [00:03<00:02, 605MB/s] model-00004-of-00011.safetensors: 42%|████▏ | 818M/1.95G [00:03<00:01, 638MB/s] model-00004-of-00011.safetensors: 55%|█████▍ | 1.07G/1.95G [00:03<00:00, 1.09GB/s] model-00004-of-00011.safetensors: 75%|███████▍ | 1.46G/1.95G [00:03<00:00, 1.78GB/s] model-00004-of-00011.safetensors: 85%|████████▌ | 1.66G/1.95G [00:03<00:00, 896MB/s] model-00004-of-00011.safetensors: 93%|█████████▎| 1.81G/1.95G [00:04<00:00, 948MB/s] model-00004-of-00011.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 404MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00005-of-00011.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00005-of-00011.safetensors: 1%| | 10.5M/1.98G [00:00<02:15, 14.5MB/s] model-00005-of-00011.safetensors: 2%|▏ | 31.5M/1.98G [00:01<01:10, 27.8MB/s] model-00005-of-00011.safetensors: 3%|▎ | 52.4M/1.98G [00:01<00:43, 44.3MB/s] model-00005-of-00011.safetensors: 5%|▌ | 105M/1.98G [00:01<00:18, 102MB/s] model-00005-of-00011.safetensors: 7%|▋ | 147M/1.98G [00:01<00:14, 124MB/s] model-00005-of-00011.safetensors: 10%|▉ | 189M/1.98G [00:02<00:11, 151MB/s] model-00005-of-00011.safetensors: 12%|█▏ | 241M/1.98G [00:02<00:08, 202MB/s] model-00005-of-00011.safetensors: 14%|█▍ | 283M/1.98G [00:02<00:07, 213MB/s] model-00005-of-00011.safetensors: 16%|█▌ | 315M/1.98G [00:02<00:07, 228MB/s] model-00005-of-00011.safetensors: 18%|█▊ | 357M/1.98G [00:02<00:06, 266MB/s] model-00005-of-00011.safetensors: 21%|██ | 419M/1.98G [00:02<00:04, 342MB/s] model-00005-of-00011.safetensors: 24%|██▍ | 482M/1.98G [00:02<00:03, 397MB/s] model-00005-of-00011.safetensors: 31%|███ | 619M/1.98G [00:02<00:02, 637MB/s] model-00005-of-00011.safetensors: 35%|███▍ | 692M/1.98G [00:03<00:02, 578MB/s] model-00005-of-00011.safetensors: 39%|███▊ | 765M/1.98G [00:03<00:02, 599MB/s] model-00005-of-00011.safetensors: 58%|█████▊ | 1.15G/1.98G [00:03<00:00, 1.43GB/s] model-00005-of-00011.safetensors: 71%|███████ | 1.41G/1.98G [00:03<00:00, 1.64GB/s] model-00005-of-00011.safetensors: 80%|███████▉ | 1.58G/1.98G [00:03<00:00, 1.09GB/s] model-00005-of-00011.safetensors: 87%|████████▋ | 1.73G/1.98G [00:03<00:00, 871MB/s] model-00005-of-00011.safetensors: 94%|█████████▎| 1.85G/1.98G [00:04<00:00, 802MB/s] model-00005-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 602MB/s] model-00005-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 437MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00006-of-00011.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00006-of-00011.safetensors: 1%| | 10.5M/1.95G [00:00<01:25, 22.8MB/s] model-00006-of-00011.safetensors: 1%| | 21.0M/1.95G [00:01<02:06, 15.2MB/s] model-00006-of-00011.safetensors: 3%|▎ | 62.9M/1.95G [00:01<00:32, 58.0MB/s] model-00006-of-00011.safetensors: 7%|▋ | 136M/1.95G [00:01<00:12, 144MB/s] model-00006-of-00011.safetensors: 12%|█▏ | 241M/1.95G [00:01<00:06, 283MB/s] model-00006-of-00011.safetensors: 16%|█▌ | 304M/1.95G [00:02<00:07, 211MB/s] model-00006-of-00011.safetensors: 18%|█▊ | 357M/1.95G [00:02<00:06, 249MB/s] model-00006-of-00011.safetensors: 23%|██▎ | 451M/1.95G [00:02<00:04, 349MB/s] model-00006-of-00011.safetensors: 27%|██▋ | 535M/1.95G [00:02<00:03, 434MB/s] model-00006-of-00011.safetensors: 32%|███▏ | 619M/1.95G [00:02<00:02, 510MB/s] model-00006-of-00011.safetensors: 36%|███▌ | 703M/1.95G [00:02<00:02, 582MB/s] model-00006-of-00011.safetensors: 42%|████▏ | 818M/1.95G [00:02<00:01, 705MB/s] model-00006-of-00011.safetensors: 51%|█████ | 996M/1.95G [00:02<00:00, 967MB/s] model-00006-of-00011.safetensors: 57%|█████▋ | 1.11G/1.95G [00:03<00:00, 857MB/s] model-00006-of-00011.safetensors: 68%|██████▊ | 1.33G/1.95G [00:03<00:00, 1.18GB/s] model-00006-of-00011.safetensors: 81%|████████▏ | 1.58G/1.95G [00:03<00:00, 1.48GB/s] model-00006-of-00011.safetensors: 90%|████████▉ | 1.75G/1.95G [00:03<00:00, 1.11GB/s] model-00006-of-00011.safetensors: 97%|█████████▋| 1.88G/1.95G [00:03<00:00, 1.14GB/s] model-00006-of-00011.safetensors: 100%|█████████▉| 1.95G/1.95G [00:12<00:00, 160MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00007-of-00011.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00007-of-00011.safetensors: 1%| | 10.5M/1.98G [00:00<02:32, 12.9MB/s] model-00007-of-00011.safetensors: 1%| | 21.0M/1.98G [00:01<01:59, 16.3MB/s] model-00007-of-00011.safetensors: 2%|▏ | 41.9M/1.98G [00:01<00:52, 37.0MB/s] model-00007-of-00011.safetensors: 5%|▍ | 94.4M/1.98G [00:01<00:19, 98.1MB/s] model-00007-of-00011.safetensors: 7%|▋ | 136M/1.98G [00:01<00:14, 126MB/s] model-00007-of-00011.safetensors: 8%|▊ | 168M/1.98G [00:01<00:12, 145MB/s] model-00007-of-00011.safetensors: 10%|▉ | 189M/1.98G [00:02<00:12, 147MB/s] model-00007-of-00011.safetensors: 12%|█▏ | 241M/1.98G [00:02<00:08, 194MB/s] model-00007-of-00011.safetensors: 14%|█▍ | 273M/1.98G [00:02<00:08, 204MB/s] model-00007-of-00011.safetensors: 16%|█▋ | 325M/1.98G [00:02<00:06, 264MB/s] model-00007-of-00011.safetensors: 20%|█▉ | 388M/1.98G [00:02<00:04, 336MB/s] model-00007-of-00011.safetensors: 26%|██▋ | 524M/1.98G [00:02<00:02, 565MB/s] model-00007-of-00011.safetensors: 30%|███ | 598M/1.98G [00:03<00:03, 427MB/s] model-00007-of-00011.safetensors: 35%|███▌ | 703M/1.98G [00:03<00:02, 546MB/s] model-00007-of-00011.safetensors: 53%|█████▎ | 1.05G/1.98G [00:03<00:00, 1.19GB/s] model-00007-of-00011.safetensors: 72%|███████▏ | 1.43G/1.98G [00:03<00:00, 1.75GB/s] model-00007-of-00011.safetensors: 83%|████████▎ | 1.64G/1.98G [00:03<00:00, 1.28GB/s] model-00007-of-00011.safetensors: 92%|█████████▏| 1.81G/1.98G [00:03<00:00, 947MB/s] model-00007-of-00011.safetensors: 99%|█████████▉| 1.96G/1.98G [00:04<00:00, 923MB/s] model-00007-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:04<00:00, 429MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00008-of-00011.safetensors: 0%| | 0.00/1.95G [00:00<?, ?B/s] model-00008-of-00011.safetensors: 1%| | 10.5M/1.95G [00:00<01:35, 20.2MB/s] model-00008-of-00011.safetensors: 1%| | 21.0M/1.95G [00:01<01:49, 17.7MB/s] model-00008-of-00011.safetensors: 2%|▏ | 31.5M/1.95G [00:01<01:26, 22.1MB/s] model-00008-of-00011.safetensors: 3%|▎ | 62.9M/1.95G [00:01<00:35, 52.8MB/s] model-00008-of-00011.safetensors: 8%|▊ | 147M/1.95G [00:01<00:11, 159MB/s] model-00008-of-00011.safetensors: 10%|▉ | 189M/1.95G [00:02<00:11, 151MB/s] model-00008-of-00011.safetensors: 12%|█▏ | 231M/1.95G [00:02<00:09, 186MB/s] model-00008-of-00011.safetensors: 16%|█▌ | 315M/1.95G [00:02<00:05, 275MB/s] model-00008-of-00011.safetensors: 19%|█▉ | 367M/1.95G [00:02<00:05, 312MB/s] model-00008-of-00011.safetensors: 22%|██▏ | 419M/1.95G [00:02<00:04, 349MB/s] model-00008-of-00011.safetensors: 24%|██▍ | 472M/1.95G [00:02<00:04, 337MB/s] model-00008-of-00011.safetensors: 27%|██▋ | 524M/1.95G [00:02<00:03, 374MB/s] model-00008-of-00011.safetensors: 33%|███▎ | 650M/1.95G [00:02<00:02, 573MB/s] model-00008-of-00011.safetensors: 38%|███▊ | 744M/1.95G [00:03<00:01, 663MB/s] model-00008-of-00011.safetensors: 43%|████▎ | 828M/1.95G [00:03<00:01, 644MB/s] model-00008-of-00011.safetensors: 50%|████▉ | 965M/1.95G [00:03<00:01, 821MB/s] model-00008-of-00011.safetensors: 76%|███████▌ | 1.48G/1.95G [00:03<00:00, 1.80GB/s] model-00008-of-00011.safetensors: 85%|████████▌ | 1.66G/1.95G [00:03<00:00, 1.08GB/s] model-00008-of-00011.safetensors: 92%|█████████▏| 1.80G/1.95G [00:04<00:00, 943MB/s] model-00008-of-00011.safetensors: 100%|█████████▉| 1.95G/1.95G [00:04<00:00, 470MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00009-of-00011.safetensors: 0%| | 0.00/1.98G [00:00<?, ?B/s] model-00009-of-00011.safetensors: 1%| | 10.5M/1.98G [00:00<02:13, 14.8MB/s] model-00009-of-00011.safetensors: 1%| | 21.0M/1.98G [00:01<01:42, 19.1MB/s] model-00009-of-00011.safetensors: 2%|▏ | 31.5M/1.98G [00:01<01:15, 25.8MB/s] model-00009-of-00011.safetensors: 5%|▌ | 105M/1.98G [00:01<00:15, 119MB/s] model-00009-of-00011.safetensors: 10%|▉ | 189M/1.98G [00:01<00:08, 219MB/s] model-00009-of-00011.safetensors: 12%|█▏ | 231M/1.98G [00:01<00:08, 209MB/s] model-00009-of-00011.safetensors: 14%|█▍ | 283M/1.98G [00:02<00:06, 247MB/s] model-00009-of-00011.safetensors: 17%|█▋ | 336M/1.98G [00:02<00:06, 270MB/s] model-00009-of-00011.safetensors: 19%|█▉ | 377M/1.98G [00:02<00:05, 299MB/s] model-00009-of-00011.safetensors: 22%|██▏ | 430M/1.98G [00:02<00:04, 347MB/s] model-00009-of-00011.safetensors: 25%|██▍ | 493M/1.98G [00:02<00:03, 404MB/s] model-00009-of-00011.safetensors: 30%|██▉ | 587M/1.98G [00:02<00:02, 493MB/s] model-00009-of-00011.safetensors: 35%|███▌ | 703M/1.98G [00:02<00:01, 645MB/s] model-00009-of-00011.safetensors: 39%|███▉ | 776M/1.98G [00:02<00:02, 518MB/s] model-00009-of-00011.safetensors: 44%|████▍ | 881M/1.98G [00:03<00:01, 632MB/s] model-00009-of-00011.safetensors: 70%|██████▉ | 1.38G/1.98G [00:03<00:00, 1.68GB/s] model-00009-of-00011.safetensors: 81%|████████ | 1.59G/1.98G [00:03<00:00, 1.47GB/s] model-00009-of-00011.safetensors: 89%|████████▉ | 1.77G/1.98G [00:03<00:00, 1.07GB/s] model-00009-of-00011.safetensors: 97%|█████████▋| 1.92G/1.98G [00:03<00:00, 1.09GB/s] model-00009-of-00011.safetensors: 100%|█████████▉| 1.98G/1.98G [00:03<00:00, 503MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00010-of-00011.safetensors: 0%| | 0.00/1.94G [00:00<?, ?B/s] model-00010-of-00011.safetensors: 1%| | 10.5M/1.94G [00:00<02:59, 10.7MB/s] model-00010-of-00011.safetensors: 1%| | 21.0M/1.94G [00:01<01:25, 22.4MB/s] model-00010-of-00011.safetensors: 2%|▏ | 41.9M/1.94G [00:01<00:37, 50.1MB/s] model-00010-of-00011.safetensors: 3%|▎ | 62.9M/1.94G [00:01<00:29, 63.4MB/s] model-00010-of-00011.safetensors: 6%|▋ | 126M/1.94G [00:01<00:11, 158MB/s] model-00010-of-00011.safetensors: 9%|▊ | 168M/1.94G [00:01<00:09, 182MB/s] model-00010-of-00011.safetensors: 10%|█ | 199M/1.94G [00:01<00:10, 165MB/s] model-00010-of-00011.safetensors: 14%|█▎ | 262M/1.94G [00:02<00:06, 240MB/s] model-00010-of-00011.safetensors: 16%|█▌ | 304M/1.94G [00:02<00:06, 255MB/s] model-00010-of-00011.safetensors: 17%|█▋ | 336M/1.94G [00:02<00:07, 221MB/s] model-00010-of-00011.safetensors: 19%|█▉ | 377M/1.94G [00:02<00:06, 255MB/s] model-00010-of-00011.safetensors: 23%|██▎ | 451M/1.94G [00:02<00:04, 329MB/s] model-00010-of-00011.safetensors: 27%|██▋ | 524M/1.94G [00:02<00:03, 392MB/s] model-00010-of-00011.safetensors: 34%|███▎ | 650M/1.94G [00:02<00:02, 588MB/s] model-00010-of-00011.safetensors: 37%|███▋ | 724M/1.94G [00:02<00:01, 615MB/s] model-00010-of-00011.safetensors: 41%|████ | 797M/1.94G [00:03<00:02, 535MB/s] model-00010-of-00011.safetensors: 59%|█████▉ | 1.14G/1.94G [00:03<00:00, 1.22GB/s] model-00010-of-00011.safetensors: 81%|████████ | 1.56G/1.94G [00:03<00:00, 1.77GB/s] model-00010-of-00011.safetensors: 91%|█████████ | 1.76G/1.94G [00:03<00:00, 1.41GB/s] model-00010-of-00011.safetensors: 99%|█████████▉| 1.93G/1.94G [00:04<00:00, 897MB/s] model-00010-of-00011.safetensors: 100%|█████████▉| 1.94G/1.94G [00:04<00:00, 449MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model-00011-of-00011.safetensors: 0%| | 0.00/1.89G [00:00<?, ?B/s] model-00011-of-00011.safetensors: 1%| | 10.5M/1.89G [00:00<02:14, 13.9MB/s] model-00011-of-00011.safetensors: 1%| | 21.0M/1.89G [00:01<01:43, 18.1MB/s] model-00011-of-00011.safetensors: 2%|▏ | 31.5M/1.89G [00:01<01:15, 24.6MB/s] model-00011-of-00011.safetensors: 3%|▎ | 52.4M/1.89G [00:01<00:38, 48.0MB/s] model-00011-of-00011.safetensors: 9%|▉ | 168M/1.89G [00:01<00:07, 220MB/s] model-00011-of-00011.safetensors: 12%|█▏ | 220M/1.89G [00:02<00:09, 181MB/s] model-00011-of-00011.safetensors: 15%|█▍ | 283M/1.89G [00:02<00:06, 244MB/s] model-00011-of-00011.safetensors: 21%|██ | 388M/1.89G [00:02<00:04, 341MB/s] model-00011-of-00011.safetensors: 23%|██▎ | 440M/1.89G [00:02<00:04, 353MB/s] model-00011-of-00011.safetensors: 27%|██▋ | 514M/1.89G [00:02<00:03, 415MB/s] model-00011-of-00011.safetensors: 33%|███▎ | 619M/1.89G [00:02<00:02, 530MB/s] model-00011-of-00011.safetensors: 37%|███▋ | 692M/1.89G [00:02<00:02, 495MB/s] model-00011-of-00011.safetensors: 44%|████▍ | 839M/1.89G [00:02<00:01, 698MB/s] model-00011-of-00011.safetensors: 75%|███████▌ | 1.43G/1.89G [00:03<00:00, 1.89GB/s] model-00011-of-00011.safetensors: 88%|████████▊ | 1.66G/1.89G [00:03<00:00, 1.62GB/s] model-00011-of-00011.safetensors: 98%|█████████▊| 1.86G/1.89G [00:03<00:00, 1.45GB/s] model-00011-of-00011.safetensors: 100%|█████████▉| 1.89G/1.89G [00:03<00:00, 498MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: model.safetensors.index.json: 0%| | 0.00/34.1k [00:00<?, ?B/s] model.safetensors.index.json: 100%|██████████| 34.1k/34.1k [00:00<00:00, 154MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: special_tokens_map.json: 0%| | 0.00/551 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 551/551 [00:00<00:00, 4.98MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 25.5MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 63.5MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/984 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 984/984 [00:00<00:00, 16.4MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: Downloaded to shared memory in 64.468s
saishf-kuro-lotus-10-7b-v3-mkmlizer: quantizing model to /dev/shm/model_cache
saishf-kuro-lotus-10-7b-v3-mkmlizer: Saving mkml model at /dev/shm/model_cache
saishf-kuro-lotus-10-7b-v3-mkmlizer: Reading /tmp/tmpzi_4kpnl/model.safetensors.index.json
saishf-kuro-lotus-10-7b-v3-mkmlizer: Profiling: 0%| | 0/435 [00:00<?, ?it/s] Profiling: 0%| | 1/435 [00:01<09:37, 1.33s/it] Profiling: 3%|▎ | 12/435 [00:01<00:37, 11.22it/s] Profiling: 5%|▍ | 21/435 [00:01<00:20, 20.64it/s] Profiling: 7%|▋ | 30/435 [00:01<00:13, 30.22it/s] Profiling: 9%|▊ | 38/435 [00:01<00:11, 35.18it/s] Profiling: 10%|█ | 45/435 [00:01<00:09, 40.56it/s] Profiling: 12%|█▏ | 53/435 [00:02<00:07, 47.83it/s] Profiling: 14%|█▍ | 60/435 [00:02<00:07, 51.62it/s] Profiling: 17%|█▋ | 72/435 [00:02<00:05, 67.75it/s] Profiling: 19%|█▊ | 81/435 [00:02<00:06, 52.87it/s] Profiling: 21%|██ | 92/435 [00:02<00:05, 62.30it/s] Profiling: 25%|██▍ | 108/435 [00:02<00:03, 81.75it/s] Profiling: 27%|██▋ | 118/435 [00:02<00:04, 68.73it/s] Profiling: 30%|██▉ | 130/435 [00:03<00:03, 76.42it/s] Profiling: 33%|███▎ | 142/435 [00:03<00:03, 86.02it/s] Profiling: 36%|███▌ | 156/435 [00:03<00:02, 97.07it/s] Profiling: 38%|███▊ | 167/435 [00:03<00:03, 76.75it/s] Profiling: 41%|████ | 177/435 [00:03<00:03, 80.10it/s] Profiling: 43%|████▎ | 187/435 [00:03<00:02, 84.66it/s] Profiling: 45%|████▌ | 197/435 [00:03<00:03, 68.92it/s] Profiling: 48%|████▊ | 208/435 [00:04<00:02, 77.61it/s] Profiling: 50%|█████ | 219/435 [00:04<00:02, 81.81it/s] Profiling: 53%|█████▎ | 230/435 [00:04<00:02, 84.77it/s] Profiling: 55%|█████▌ | 240/435 [00:04<00:02, 72.81it/s] Profiling: 58%|█████▊ | 252/435 [00:04<00:02, 83.42it/s] Profiling: 61%|██████ | 266/435 [00:04<00:01, 95.77it/s] Profiling: 64%|██████▎ | 277/435 [00:04<00:01, 93.53it/s] Profiling: 66%|██████▌ | 287/435 [00:04<00:01, 75.12it/s] Profiling: 69%|██████▉ | 300/435 [00:05<00:01, 84.65it/s] Profiling: 71%|███████▏ | 311/435 [00:05<00:01, 87.00it/s] Profiling: 74%|███████▍ | 321/435 [00:05<00:01, 77.47it/s] Profiling: 76%|███████▋ | 332/435 [00:05<00:01, 84.63it/s] Profiling: 80%|███████▉ | 347/435 [00:05<00:00, 99.28it/s] Profiling: 82%|████████▏ | 358/435 [00:05<00:00, 98.55it/s] Profiling: 85%|████████▍ | 369/435 [00:05<00:00, 79.21it/s] Profiling: 88%|████████▊ | 381/435 [00:06<00:00, 88.22it/s] Profiling: 90%|█████████ | 392/435 [00:06<00:00, 89.78it/s] Profiling: 92%|█████████▏| 402/435 [00:07<00:01, 20.96it/s] Profiling: 96%|█████████▌| 418/435 [00:07<00:00, 30.99it/s] Profiling: 98%|█████████▊| 428/435 [00:07<00:00, 37.09it/s] Profiling: 100%|██████████| 435/435 [00:07<00:00, 54.71it/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: quantized model in 23.575s
saishf-kuro-lotus-10-7b-v3-mkmlizer: creating bucket guanaco-mkml-models
saishf-kuro-lotus-10-7b-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
saishf-kuro-lotus-10-7b-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v3
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v3/special_tokens_map.json
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v3/config.json
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v3/tokenizer_config.json
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v3/tokenizer.model
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v3/tokenizer.json
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/saishf-kuro-lotus-10-7b-v3/mkml_model.tensors
saishf-kuro-lotus-10-7b-v3-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
saishf-kuro-lotus-10-7b-v3-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.
saishf-kuro-lotus-10-7b-v3-mkmlizer: warnings.warn(
saishf-kuro-lotus-10-7b-v3-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 8.69MB/s]
saishf-kuro-lotus-10-7b-v3-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.
saishf-kuro-lotus-10-7b-v3-mkmlizer: warnings.warn(
saishf-kuro-lotus-10-7b-v3-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.10MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 32.3MB/s]
saishf-kuro-lotus-10-7b-v3-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 6.73MB/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 6.72MB/s]
saishf-kuro-lotus-10-7b-v3-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.
saishf-kuro-lotus-10-7b-v3-mkmlizer: warnings.warn(
saishf-kuro-lotus-10-7b-v3-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
saishf-kuro-lotus-10-7b-v3-mkmlizer: Saving duration: 0.276s
saishf-kuro-lotus-10-7b-v3-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.474s
saishf-kuro-lotus-10-7b-v3-mkmlizer: creating bucket guanaco-reward-models
saishf-kuro-lotus-10-7b-v3-mkmlizer: Bucket 's3://guanaco-reward-models/' created
saishf-kuro-lotus-10-7b-v3-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/saishf-kuro-lotus-10-7b-v3_reward
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/saishf-kuro-lotus-10-7b-v3_reward/config.json
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/saishf-kuro-lotus-10-7b-v3_reward/tokenizer_config.json
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/saishf-kuro-lotus-10-7b-v3_reward/special_tokens_map.json
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/saishf-kuro-lotus-10-7b-v3_reward/vocab.json
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/saishf-kuro-lotus-10-7b-v3_reward/merges.txt
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/saishf-kuro-lotus-10-7b-v3_reward/tokenizer.json
saishf-kuro-lotus-10-7b-v3-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/saishf-kuro-lotus-10-7b-v3_reward/reward.tensors
Job saishf-kuro-lotus-10-7b-v3-mkmlizer completed after 116.97s with status: succeeded
Stopping job with name saishf-kuro-lotus-10-7b-v3-mkmlizer
Pipeline stage MKMLizer completed in 118.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service saishf-kuro-lotus-10-7b-v3
Waiting for inference service saishf-kuro-lotus-10-7b-v3 to be ready
Failed to get response for submission anhnv125-llama-op-v17-1_v32: ('http://anhnv125-llama-op-v17-1-v32-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:57608->127.0.0.1:8080: read: connection reset by peer\n')
Exception raised while processing tagging_function
Traceback (most recent call last): File "/code/guanaco/guanaco_services/src/guanaco_model_service/chat_api.py", line 274, in resolve_chat_api conversation_tag = self.tagging_function(conversation_state) File "/home/zongyi/gitlab/zztools/zztools/llm/guanaco/submit_routing_model.py", line 176, in last_user_message_length TypeError: 'ConversationState' object is not subscriptable
Inference service saishf-kuro-lotus-10-7b-v3 ready after 50.3598518371582s
Pipeline stage ISVCDeployer completed in 56.83s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7397899627685547s
Received healthy response to inference request in 0.6653866767883301s
Received healthy response to inference request in 0.5678648948669434s
Received healthy response to inference request in 0.9962308406829834s
Received healthy response to inference request in 1.5440456867218018s
5 requests
0 failed requests
5th percentile: 0.5873692512512207
10th percentile: 0.606873607635498
20th percentile: 0.6458823204040527
30th percentile: 0.7315555095672608
40th percentile: 0.8638931751251221
50th percentile: 0.9962308406829834
60th percentile: 1.2153567790985107
70th percentile: 1.434482717514038
80th percentile: 1.5831945419311524
90th percentile: 1.6614922523498534
95th percentile: 1.700641107559204
99th percentile: 1.7319601917266845
mean time: 1.1026636123657227
Pipeline stage StressChecker completed in 6.39s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.05s
M-Eval Dataset for topic stay_in_character is loaded
saishf-kuro-lotus-10-7b_v3 status is now deployed due to DeploymentManager action
saishf-kuro-lotus-10-7b_v3 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics