submission_id: nitral-ai-kukulstanta-7b_v5
developer_uid: chai_backend_admin
status: inactive
model_repo: Nitral-AI/KukulStanta-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: 2024-04-02T04:45:53+00:00
model_name: auto_submit_ricum_vovedebepa
model_eval_status: success
safety_score: 0.98
entertaining: 6.76
stay_in_character: 8.54
user_preference: 7.48
double_thumbs_up: 60
thumbs_up: 84
thumbs_down: 41
num_battles: 5375
num_wins: 2465
win_ratio: 0.4586046511627907
celo_rating: 1132.92
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-kukulstanta-7b-v5-mkmlizer
Waiting for job on nitral-ai-kukulstanta-7b-v5-mkmlizer to finish
nitral-ai-kukulstanta-7b-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ _____ __ __ ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ /___/ ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ Version: 0.6.11 ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ belonging to: ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ║ ║
nitral-ai-kukulstanta-7b-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-kukulstanta-7b-v5-mkmlizer: .gitattributes: 0%| | 0.00/1.52k [00:00<?, ?B/s] .gitattributes: 100%|██████████| 1.52k/1.52k [00:00<00:00, 19.0MB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: README.md: 0%| | 0.00/778 [00:00<?, ?B/s] README.md: 100%|██████████| 778/778 [00:00<00:00, 6.44MB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: config.json: 0%| | 0.00/637 [00:00<?, ?B/s] config.json: 100%|██████████| 637/637 [00:00<00:00, 4.74MB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: mergekit_config.yml: 0%| | 0.00/370 [00:00<?, ?B/s] mergekit_config.yml: 100%|██████████| 370/370 [00:00<00:00, 3.05MB/s]
nitral-ai-kukulstanta-7b-v5-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<00:22, 89.0MB/s] model-00001-of-00008.safetensors: 2%|▏ | 31.5M/1.98G [00:00<00:14, 138MB/s] model-00001-of-00008.safetensors: 3%|▎ | 62.9M/1.98G [00:00<00:16, 119MB/s] model-00001-of-00008.safetensors: 11%|█ | 220M/1.98G [00:00<00:04, 434MB/s] model-00001-of-00008.safetensors: 14%|█▍ | 273M/1.98G [00:00<00:04, 415MB/s] model-00001-of-00008.safetensors: 16%|█▋ | 325M/1.98G [00:00<00:03, 441MB/s] model-00001-of-00008.safetensors: 19%|█▉ | 377M/1.98G [00:01<00:03, 432MB/s] model-00001-of-00008.safetensors: 45%|████▌ | 891M/1.98G [00:01<00:00, 1.63GB/s] model-00001-of-00008.safetensors: 70%|██████▉ | 1.38G/1.98G [00:01<00:00, 2.44GB/s] model-00001-of-00008.safetensors: 84%|████████▍ | 1.67G/1.98G [00:01<00:00, 2.27GB/s] model-00001-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:05<00:00, 386MB/s]
nitral-ai-kukulstanta-7b-v5-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<01:04, 30.1MB/s] model-00002-of-00008.safetensors: 1%| | 21.0M/1.95G [00:00<00:42, 45.8MB/s] model-00002-of-00008.safetensors: 3%|▎ | 62.9M/1.95G [00:00<00:19, 97.6MB/s] model-00002-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:00<00:16, 115MB/s] model-00002-of-00008.safetensors: 15%|█▌ | 294M/1.95G [00:01<00:03, 544MB/s] model-00002-of-00008.safetensors: 58%|█████▊ | 1.12G/1.95G [00:01<00:00, 2.35GB/s] model-00002-of-00008.safetensors: 75%|███████▍ | 1.45G/1.95G [00:01<00:00, 2.03GB/s] model-00002-of-00008.safetensors: 89%|████████▊ | 1.73G/1.95G [00:01<00:00, 1.84GB/s] model-00002-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.26GB/s]
nitral-ai-kukulstanta-7b-v5-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<01:05, 30.1MB/s] model-00003-of-00008.safetensors: 1%| | 21.0M/1.98G [00:00<00:42, 46.5MB/s] model-00003-of-00008.safetensors: 4%|▍ | 83.9M/1.98G [00:00<00:10, 185MB/s] model-00003-of-00008.safetensors: 6%|▌ | 115M/1.98G [00:00<00:11, 163MB/s] model-00003-of-00008.safetensors: 7%|▋ | 136M/1.98G [00:00<00:11, 165MB/s] model-00003-of-00008.safetensors: 35%|███▌ | 703M/1.98G [00:01<00:00, 1.42GB/s] model-00003-of-00008.safetensors: 66%|██████▌ | 1.31G/1.98G [00:01<00:00, 2.36GB/s] model-00003-of-00008.safetensors: 81%|████████ | 1.60G/1.98G [00:01<00:00, 1.77GB/s] model-00003-of-00008.safetensors: 100%|█████████▉| 1.98G/1.98G [00:01<00:00, 1.26GB/s]
nitral-ai-kukulstanta-7b-v5-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<01:05, 29.6MB/s] model-00004-of-00008.safetensors: 1%| | 21.0M/1.95G [00:00<00:40, 47.7MB/s] model-00004-of-00008.safetensors: 5%|▌ | 105M/1.95G [00:00<00:07, 249MB/s] model-00004-of-00008.safetensors: 8%|▊ | 147M/1.95G [00:00<00:08, 219MB/s] model-00004-of-00008.safetensors: 20%|██ | 398M/1.95G [00:00<00:02, 727MB/s] model-00004-of-00008.safetensors: 66%|██████▌ | 1.28G/1.95G [00:01<00:00, 2.67GB/s] model-00004-of-00008.safetensors: 85%|████████▍ | 1.65G/1.95G [00:01<00:00, 1.73GB/s] model-00004-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.34GB/s]
nitral-ai-kukulstanta-7b-v5-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<01:05, 29.0MB/s] model-00006-of-00008.safetensors: 1%| | 21.0M/1.92G [00:00<00:47, 40.2MB/s] model-00006-of-00008.safetensors: 7%|▋ | 126M/1.92G [00:00<00:06, 263MB/s] model-00006-of-00008.safetensors: 9%|▊ | 168M/1.92G [00:00<00:07, 244MB/s] model-00006-of-00008.safetensors: 10%|█ | 199M/1.92G [00:01<00:06, 248MB/s] model-00006-of-00008.safetensors: 17%|█▋ | 336M/1.92G [00:01<00:03, 502MB/s] model-00006-of-00008.safetensors: 64%|██████▍ | 1.23G/1.92G [00:01<00:00, 2.56GB/s] model-00006-of-00008.safetensors: 81%|████████ | 1.56G/1.92G [00:01<00:00, 1.92GB/s] model-00006-of-00008.safetensors: 100%|█████████▉| 1.92G/1.92G [00:01<00:00, 1.22GB/s]
nitral-ai-kukulstanta-7b-v5-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<01:12, 26.7MB/s] model-00007-of-00008.safetensors: 1%| | 21.0M/1.95G [00:00<00:41, 46.3MB/s] model-00007-of-00008.safetensors: 4%|▍ | 83.9M/1.95G [00:00<00:10, 183MB/s] model-00007-of-00008.safetensors: 6%|▌ | 115M/1.95G [00:00<00:10, 171MB/s] model-00007-of-00008.safetensors: 16%|█▌ | 315M/1.95G [00:00<00:02, 578MB/s] model-00007-of-00008.safetensors: 59%|█████▉ | 1.15G/1.95G [00:01<00:00, 2.44GB/s] model-00007-of-00008.safetensors: 76%|███████▋ | 1.48G/1.95G [00:01<00:00, 2.07GB/s] model-00007-of-00008.safetensors: 90%|█████████ | 1.76G/1.95G [00:01<00:00, 1.91GB/s] model-00007-of-00008.safetensors: 100%|█████████▉| 1.95G/1.95G [00:01<00:00, 1.32GB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: model-00008-of-00008.safetensors: 0%| | 0.00/872M [00:00<?, ?B/s] model-00008-of-00008.safetensors: 0%| | 2.13M/872M [00:00<00:52, 16.6MB/s] model-00008-of-00008.safetensors: 15%|█▍ | 128M/872M [00:00<00:01, 638MB/s] model-00008-of-00008.safetensors: 23%|██▎ | 201M/872M [00:00<00:01, 581MB/s] model-00008-of-00008.safetensors: 51%|█████ | 443M/872M [00:00<00:00, 1.20GB/s] model-00008-of-00008.safetensors: 100%|█████████▉| 872M/872M [00:00<00:00, 1.60GB/s]
nitral-ai-kukulstanta-7b-v5-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, 136MB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: special_tokens_map.json: 0%| | 0.00/414 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 414/414 [00:00<00:00, 4.08MB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: tokenizer.json: 0%| | 0.00/1.80M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 1.80M/1.80M [00:00<00:00, 44.1MB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: tokenizer.model: 0%| | 0.00/493k [00:00<?, ?B/s] tokenizer.model: 100%|██████████| 493k/493k [00:00<00:00, 60.8MB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: tokenizer_config.json: 0%| | 0.00/967 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 967/967 [00:00<00:00, 11.2MB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: Downloaded to shared memory in 16.790s
nitral-ai-kukulstanta-7b-v5-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-kukulstanta-7b-v5-mkmlizer: Saving mkml model at /dev/shm/model_cache
nitral-ai-kukulstanta-7b-v5-mkmlizer: Reading /tmp/tmp9af3jav1/model.safetensors.index.json
nitral-ai-kukulstanta-7b-v5-mkmlizer: Profiling: 0%| | 0/291 [00:00<?, ?it/s] Profiling: 0%| | 1/291 [00:00<01:16, 3.80it/s] Profiling: 7%|▋ | 19/291 [00:00<00:04, 65.08it/s] Profiling: 13%|█▎ | 37/291 [00:00<00:03, 83.07it/s] Profiling: 20%|█▉ | 57/291 [00:00<00:02, 112.32it/s] Profiling: 27%|██▋ | 80/291 [00:00<00:01, 123.63it/s] Profiling: 33%|███▎ | 95/291 [00:00<00:01, 129.96it/s] Profiling: 41%|████ | 119/291 [00:01<00:01, 131.06it/s] Profiling: 47%|████▋ | 138/291 [00:01<00:01, 144.92it/s] Profiling: 55%|█████▍ | 160/291 [00:02<00:03, 37.68it/s] Profiling: 62%|██████▏ | 181/291 [00:02<00:02, 50.68it/s] Profiling: 68%|██████▊ | 197/291 [00:03<00:03, 29.39it/s] Profiling: 74%|███████▍ | 215/291 [00:04<00:01, 38.70it/s] Profiling: 79%|███████▉ | 231/291 [00:04<00:01, 46.70it/s] Profiling: 86%|████████▌ | 250/291 [00:04<00:00, 61.06it/s] Profiling: 94%|█████████▍| 274/291 [00:04<00:00, 75.91it/s] Profiling: 100%|██████████| 291/291 [00:04<00:00, 63.20it/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: quantized model in 14.267s
nitral-ai-kukulstanta-7b-v5-mkmlizer: Processed model Nitral-AI/KukulStanta-7B in 31.845s
nitral-ai-kukulstanta-7b-v5-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-kukulstanta-7b-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-kukulstanta-7b-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-kukulstanta-7b-v5
nitral-ai-kukulstanta-7b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-kukulstanta-7b-v5/tokenizer_config.json
nitral-ai-kukulstanta-7b-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-kukulstanta-7b-v5/special_tokens_map.json
nitral-ai-kukulstanta-7b-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-kukulstanta-7b-v5/config.json
nitral-ai-kukulstanta-7b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-kukulstanta-7b-v5/tokenizer.json
nitral-ai-kukulstanta-7b-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/nitral-ai-kukulstanta-7b-v5/tokenizer.model
nitral-ai-kukulstanta-7b-v5-mkmlizer: cp /dev/shm/model_cache/mkml_model.tensors s3://guanaco-mkml-models/nitral-ai-kukulstanta-7b-v5/mkml_model.tensors
nitral-ai-kukulstanta-7b-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-kukulstanta-7b-v5-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.
nitral-ai-kukulstanta-7b-v5-mkmlizer: warnings.warn(
nitral-ai-kukulstanta-7b-v5-mkmlizer: config.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] config.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 11.2MB/s]
nitral-ai-kukulstanta-7b-v5-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.
nitral-ai-kukulstanta-7b-v5-mkmlizer: warnings.warn(
nitral-ai-kukulstanta-7b-v5-mkmlizer: tokenizer_config.json: 0%| | 0.00/234 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 234/234 [00:00<00:00, 2.67MB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: vocab.json: 0%| | 0.00/1.04M [00:00<?, ?B/s] vocab.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 36.4MB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 2.11M/2.11M [00:00<00:00, 41.6MB/s]
nitral-ai-kukulstanta-7b-v5-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.
nitral-ai-kukulstanta-7b-v5-mkmlizer: warnings.warn(
nitral-ai-kukulstanta-7b-v5-mkmlizer: pytorch_model.bin: 0%| | 0.00/1.44G [00:00<?, ?B/s] pytorch_model.bin: 1%|▏ | 21.0M/1.44G [00:00<00:09, 151MB/s] pytorch_model.bin: 3%|▎ | 41.9M/1.44G [00:00<00:13, 103MB/s] pytorch_model.bin: 18%|█▊ | 262M/1.44G [00:00<00:01, 598MB/s] pytorch_model.bin: 23%|██▎ | 336M/1.44G [00:01<00:03, 286MB/s] pytorch_model.bin: 33%|███▎ | 482M/1.44G [00:01<00:02, 454MB/s] pytorch_model.bin: 91%|█████████▏| 1.32G/1.44G [00:01<00:00, 1.79GB/s] pytorch_model.bin: 100%|█████████▉| 1.44G/1.44G [00:01<00:00, 1.04GB/s]
nitral-ai-kukulstanta-7b-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-kukulstanta-7b-v5-mkmlizer: Saving duration: 0.212s
nitral-ai-kukulstanta-7b-v5-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.152s
nitral-ai-kukulstanta-7b-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-kukulstanta-7b-v5_reward/reward.tensors
Job nitral-ai-kukulstanta-7b-v5-mkmlizer completed after 64.19s with status: succeeded
Stopping job with name nitral-ai-kukulstanta-7b-v5-mkmlizer
Pipeline stage MKMLizer completed in 65.08s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-kukulstanta-7b-v5
Waiting for inference service nitral-ai-kukulstanta-7b-v5 to be ready
Inference service nitral-ai-kukulstanta-7b-v5 ready after 91.13771533966064s
Pipeline stage ISVCDeployer completed in 97.08s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.132077693939209s
Received healthy response to inference request in 0.4958765506744385s
Received healthy response to inference request in 0.6624281406402588s
Received healthy response to inference request in 1.0358808040618896s
Received healthy response to inference request in 0.7175800800323486s
5 requests
0 failed requests
5th percentile: 0.5291868686676026
10th percentile: 0.5624971866607666
20th percentile: 0.6291178226470947
30th percentile: 0.6734585285186767
40th percentile: 0.6955193042755127
50th percentile: 0.7175800800323486
60th percentile: 0.844900369644165
70th percentile: 0.9722206592559814
80th percentile: 1.0551201820373535
90th percentile: 1.0935989379882813
95th percentile: 1.1128383159637452
99th percentile: 1.1282298183441162
mean time: 0.8087686538696289
Pipeline stage StressChecker completed in 4.83s
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
nitral-ai-kukulstanta-7b_v5 status is now deployed due to DeploymentManager action
nitral-ai-kukulstanta-7b_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics