koboldai-llama2-13b-ti_20758

developer_uid: huohuo12
submission_id: koboldai-llama2-13b-ti_20758_v10
model_name: koboldai-llama2-13b-ti_20758_v10
model_group: KoboldAI/LLaMA2-13B-Tief
status: torndown
timestamp: 2025-02-18T03:15:03+00:00
num_battles: 6438
num_wins: 2874
celo_rating: 1204.85
family_friendly_score: 0.6033999999999999
family_friendly_standard_error: 0.006918214220447355
submission_type: basic
model_repo: KoboldAI/LLaMA2-13B-Tiefighter
model_architecture: LlamaForCausalLM
model_num_parameters: 13015864320.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: koboldai-llama2-13b-ti_20758_v10
is_internal_developer: False
language_model: KoboldAI/LLaMA2-13B-Tiefighter
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-17
win_ratio: 0.44641192917054984
generation_params: {'temperature': 0.8, 'top_p': 0.87, 'min_p': 0.015, 'top_k': 45, 'presence_penalty': 0.65, 'frequency_penalty': 0.35, '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 koboldai-llama2-13b-ti-20758-v10-mkmlizer
Waiting for job on koboldai-llama2-13b-ti-20758-v10-mkmlizer to finish
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║     _____            __           __                                ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║       /___/                                                         ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║                                                                     ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║  Version: 0.12.8                                                    ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║  https://mk1.ai                                                     ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║                                                                     ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║  belonging to:                                                      ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║                                                                     ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║  Chai Research Corp.                                                ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ║                                                                     ║
koboldai-llama2-13b-ti-20758-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
koboldai-llama2-13b-ti-20758-v10-mkmlizer: Downloaded to shared memory in 23.946s
koboldai-llama2-13b-ti-20758-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwmzvt08m, device:0
koboldai-llama2-13b-ti-20758-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
koboldai-llama2-13b-ti-20758-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/mk1/flywheel/functional/loader.py:55: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
koboldai-llama2-13b-ti-20758-v10-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
koboldai-llama2-13b-ti-20758-v10-mkmlizer: quantized model in 28.285s
koboldai-llama2-13b-ti-20758-v10-mkmlizer: Processed model KoboldAI/LLaMA2-13B-Tiefighter in 52.232s
koboldai-llama2-13b-ti-20758-v10-mkmlizer: creating bucket guanaco-mkml-models
koboldai-llama2-13b-ti-20758-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
koboldai-llama2-13b-ti-20758-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/koboldai-llama2-13b-ti-20758-v10
koboldai-llama2-13b-ti-20758-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/koboldai-llama2-13b-ti-20758-v10/config.json
koboldai-llama2-13b-ti-20758-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/koboldai-llama2-13b-ti-20758-v10/tokenizer_config.json
koboldai-llama2-13b-ti-20758-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/koboldai-llama2-13b-ti-20758-v10/special_tokens_map.json
koboldai-llama2-13b-ti-20758-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/koboldai-llama2-13b-ti-20758-v10/tokenizer.model
koboldai-llama2-13b-ti-20758-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/koboldai-llama2-13b-ti-20758-v10/tokenizer.json
koboldai-llama2-13b-ti-20758-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/koboldai-llama2-13b-ti-20758-v10/flywheel_model.0.safetensors
koboldai-llama2-13b-ti-20758-v10-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 36.25it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:05, 64.29it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:04, 72.05it/s]
Loading 0:   9%|▉         | 34/363 [00:00<00:04, 74.51it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:04, 77.60it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:04, 76.98it/s]
Loading 0:  17%|█▋        | 61/363 [00:00<00:03, 77.15it/s]
Loading 0:  19%|█▉        | 70/363 [00:00<00:03, 76.41it/s]
Loading 0:  22%|██▏       | 79/363 [00:01<00:03, 79.31it/s]
Loading 0:  24%|██▍       | 88/363 [00:01<00:03, 81.90it/s]
Loading 0:  27%|██▋       | 97/363 [00:01<00:03, 83.83it/s]
Loading 0:  29%|██▉       | 106/363 [00:01<00:03, 84.28it/s]
Loading 0:  32%|███▏      | 115/363 [00:01<00:02, 83.48it/s]
Loading 0:  34%|███▍      | 124/363 [00:01<00:03, 72.56it/s]
Loading 0:  37%|███▋      | 133/363 [00:01<00:03, 76.34it/s]
Loading 0:  39%|███▉      | 142/363 [00:01<00:02, 79.60it/s]
Loading 0:  42%|████▏     | 151/363 [00:04<00:17, 12.07it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:10, 19.19it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:07, 25.62it/s]
Loading 0:  52%|█████▏    | 187/363 [00:04<00:05, 31.33it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 42.88it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 50.45it/s]
Loading 0:  61%|██████▏   | 223/363 [00:04<00:02, 56.51it/s]
Loading 0:  64%|██████▍   | 232/363 [00:04<00:02, 60.50it/s]
Loading 0:  66%|██████▋   | 241/363 [00:05<00:01, 62.19it/s]
Loading 0:  69%|██████▉   | 250/363 [00:05<00:01, 67.81it/s]
Loading 0:  72%|███████▏  | 260/363 [00:05<00:01, 75.09it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 82.56it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:00, 83.78it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:03, 22.23it/s]
Loading 0:  85%|████████▌ | 310/363 [00:06<00:01, 31.52it/s]
Loading 0:  88%|████████▊ | 319/363 [00:07<00:01, 36.95it/s]
Loading 0:  90%|█████████ | 328/363 [00:07<00:00, 43.16it/s]
Loading 0:  93%|█████████▎| 337/363 [00:07<00:00, 49.88it/s]
Loading 0:  96%|█████████▌| 349/363 [00:07<00:00, 58.38it/s]
Loading 0:  99%|█████████▊| 358/363 [00:07<00:00, 64.01it/s]
                                                            
Job koboldai-llama2-13b-ti-20758-v10-mkmlizer completed after 83.91s with status: succeeded
Stopping job with name koboldai-llama2-13b-ti-20758-v10-mkmlizer
Pipeline stage MKMLizer completed in 84.45s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service koboldai-llama2-13b-ti-20758-v10
Waiting for inference service koboldai-llama2-13b-ti-20758-v10 to be ready
Failed to get response for submission chaiml-dn-20250217-c-4ep_8638_v1: HTTPConnectionPool(host='chaiml-dn-20250217-c-4ep-8638-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission koboldai-llama2-13b-tie_20758_v7: HTTPConnectionPool(host='koboldai-llama2-13b-tie-20758-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service koboldai-llama2-13b-ti-20758-v10 ready after 210.8516652584076s
Pipeline stage MKMLDeployer completed in 211.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6301653385162354s
Received healthy response to inference request in 1.7848854064941406s
Received healthy response to inference request in 1.8142790794372559s
Received healthy response to inference request in 1.7360594272613525s
Received healthy response to inference request in 1.9740142822265625s
5 requests
0 failed requests
5th percentile: 1.7458246231079102
10th percentile: 1.7555898189544679
20th percentile: 1.775120210647583
30th percentile: 1.7907641410827637
40th percentile: 1.8025216102600097
50th percentile: 1.8142790794372559
60th percentile: 1.8781731605529786
70th percentile: 1.942067241668701
80th percentile: 2.105244493484497
90th percentile: 2.367704916000366
95th percentile: 2.4989351272583007
99th percentile: 2.6039192962646482
mean time: 1.9878807067871094
Pipeline stage StressChecker completed in 11.29s
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 0.66s
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 0.69s
Shutdown handler de-registered
koboldai-llama2-13b-ti_20758_v10 status is now deployed due to DeploymentManager action
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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4814.23s
Shutdown handler de-registered
koboldai-llama2-13b-ti_20758_v10 status is now inactive due to auto deactivation removed underperforming models
koboldai-llama2-13b-ti_20758_v10 status is now torndown due to DeploymentManager action
koboldai-llama2-13b-ti_20758_v10 status is now torndown due to DeploymentManager action
koboldai-llama2-13b-ti_20758_v10 status is now torndown due to DeploymentManager action