koboldai-llama2-13b-tie_20758

developer_uid: huohuo12
submission_id: koboldai-llama2-13b-tie_20758_v6
model_name: koboldai-llama2-13b-tie_20758_v6
model_group: KoboldAI/LLaMA2-13B-Tief
status: torndown
timestamp: 2025-02-18T03:08:29+00:00
num_battles: 6498
num_wins: 2949
celo_rating: 1212.24
family_friendly_score: 0.6075999999999999
family_friendly_standard_error: 0.006905392675293709
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-tie_20758_v6
is_internal_developer: False
language_model: KoboldAI/LLaMA2-13B-Tiefighter
model_size: 13B
ranking_group: single
us_pacific_date: 2025-02-17
win_ratio: 0.4538319482917821
generation_params: {'temperature': 0.8, 'top_p': 0.85, 'min_p': 0.015, 'top_k': 50, 'presence_penalty': 0.7, 'frequency_penalty': 0.25, '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-tie-20758-v6-mkmlizer
Waiting for job on koboldai-llama2-13b-tie-20758-v6-mkmlizer to finish
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║     _____            __           __                                ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║       /___/                                                         ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║                                                                     ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║  Version: 0.12.8                                                    ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║  https://mk1.ai                                                     ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║                                                                     ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║  belonging to:                                                      ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║                                                                     ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║  Chai Research Corp.                                                ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ║                                                                     ║
koboldai-llama2-13b-tie-20758-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
koboldai-llama2-13b-tie-20758-v6-mkmlizer: Downloaded to shared memory in 26.216s
koboldai-llama2-13b-tie-20758-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxdb2lg2z, device:0
koboldai-llama2-13b-tie-20758-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
koboldai-llama2-13b-tie-20758-v6-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-tie-20758-v6-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
koboldai-llama2-13b-tie-20758-v6-mkmlizer: quantized model in 27.786s
koboldai-llama2-13b-tie-20758-v6-mkmlizer: Processed model KoboldAI/LLaMA2-13B-Tiefighter in 54.002s
koboldai-llama2-13b-tie-20758-v6-mkmlizer: creating bucket guanaco-mkml-models
koboldai-llama2-13b-tie-20758-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
koboldai-llama2-13b-tie-20758-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v6
koboldai-llama2-13b-tie-20758-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v6/config.json
koboldai-llama2-13b-tie-20758-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v6/tokenizer_config.json
koboldai-llama2-13b-tie-20758-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v6/special_tokens_map.json
koboldai-llama2-13b-tie-20758-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v6/tokenizer.model
koboldai-llama2-13b-tie-20758-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v6/tokenizer.json
koboldai-llama2-13b-tie-20758-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/koboldai-llama2-13b-tie-20758-v6/flywheel_model.0.safetensors
koboldai-llama2-13b-tie-20758-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 33.68it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:05, 65.74it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:03, 84.97it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:03, 92.66it/s]
Loading 0:  14%|█▍        | 52/363 [00:00<00:03, 83.15it/s]
Loading 0:  18%|█▊        | 67/363 [00:00<00:03, 90.44it/s]
Loading 0:  22%|██▏       | 79/363 [00:00<00:03, 87.12it/s]
Loading 0:  24%|██▍       | 88/363 [00:01<00:03, 87.12it/s]
Loading 0:  28%|██▊       | 102/363 [00:01<00:02, 100.96it/s]
Loading 0:  31%|███       | 113/363 [00:01<00:02, 86.59it/s] 
Loading 0:  34%|███▍      | 124/363 [00:01<00:02, 83.93it/s]
Loading 0:  37%|███▋      | 133/363 [00:01<00:02, 82.65it/s]
Loading 0:  39%|███▉      | 142/363 [00:01<00:02, 84.27it/s]
Loading 0:  42%|████▏     | 151/363 [00:03<00:16, 12.70it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:12, 16.77it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:07, 25.40it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:05, 31.13it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:04, 39.13it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:03, 45.79it/s]
Loading 0:  61%|██████    | 220/363 [00:04<00:02, 57.98it/s]
Loading 0:  64%|██████▍   | 232/363 [00:04<00:02, 62.59it/s]
Loading 0:  66%|██████▋   | 241/363 [00:04<00:01, 66.98it/s]
Loading 0:  69%|██████▉   | 250/363 [00:05<00:01, 71.59it/s]
Loading 0:  73%|███████▎  | 265/363 [00:05<00:01, 82.01it/s]
Loading 0:  76%|███████▌  | 275/363 [00:05<00:01, 83.53it/s]
Loading 0:  79%|███████▊  | 285/363 [00:05<00:00, 87.48it/s]
Loading 0:  81%|████████▏ | 295/363 [00:06<00:03, 20.58it/s]
Loading 0:  84%|████████▎ | 304/363 [00:06<00:02, 25.79it/s]
Loading 0:  88%|████████▊ | 319/363 [00:07<00:01, 36.66it/s]
Loading 0:  90%|█████████ | 328/363 [00:07<00:00, 41.92it/s]
Loading 0:  93%|█████████▎| 337/363 [00:07<00:00, 48.56it/s]
Loading 0:  95%|█████████▌| 346/363 [00:07<00:00, 55.49it/s]
Loading 0:  99%|█████████▊| 358/363 [00:07<00:00, 62.89it/s]
                                                            
Job koboldai-llama2-13b-tie-20758-v6-mkmlizer completed after 83.62s with status: succeeded
Stopping job with name koboldai-llama2-13b-tie-20758-v6-mkmlizer
Pipeline stage MKMLizer completed in 84.10s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service koboldai-llama2-13b-tie-20758-v6
Waiting for inference service koboldai-llama2-13b-tie-20758-v6 to be ready
Inference service koboldai-llama2-13b-tie-20758-v6 ready after 210.9061553478241s
Pipeline stage MKMLDeployer completed in 211.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5010547637939453s
Received healthy response to inference request in 1.9214465618133545s
Received healthy response to inference request in 1.7271347045898438s
Received healthy response to inference request in 1.8704233169555664s
Received healthy response to inference request in 1.7799618244171143s
5 requests
0 failed requests
5th percentile: 1.7377001285552978
10th percentile: 1.748265552520752
20th percentile: 1.7693964004516602
30th percentile: 1.7980541229248046
40th percentile: 1.8342387199401855
50th percentile: 1.8704233169555664
60th percentile: 1.8908326148986816
70th percentile: 1.9112419128417968
80th percentile: 2.0373682022094726
90th percentile: 2.269211483001709
95th percentile: 2.3851331233978272
99th percentile: 2.477870435714722
mean time: 1.9600042343139648
Pipeline stage StressChecker completed in 10.93s
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 0.62s
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 0.64s
Shutdown handler de-registered
koboldai-llama2-13b-tie_20758_v6 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service koboldai-llama2-13b-tie-20758-v6-profiler
Waiting for inference service koboldai-llama2-13b-tie-20758-v6-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5162.15s
Shutdown handler de-registered
koboldai-llama2-13b-tie_20758_v6 status is now inactive due to auto deactivation removed underperforming models
koboldai-llama2-13b-tie_20758_v6 status is now torndown due to DeploymentManager action
koboldai-llama2-13b-tie_20758_v6 status is now torndown due to DeploymentManager action
koboldai-llama2-13b-tie_20758_v6 status is now torndown due to DeploymentManager action