austism-chronos-hermes-13b

developer_uid: fengjiayi
submission_id: austism-chronos-hermes-13b_v1
model_name: austism-chronos-hermes-13b_v1
model_group: Austism/chronos-hermes-1
status: torndown
timestamp: 2025-01-23T05:29:49+00:00
num_battles: 7360
num_wins: 3313
celo_rating: 1188.91
family_friendly_score: 0.5962000000000001
family_friendly_standard_error: 0.006938956117457438
submission_type: basic
model_repo: Austism/chronos-hermes-13b
model_architecture: LlamaForCausalLM
model_num_parameters: 13015874560.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: austism-chronos-hermes-13b_v1
is_internal_developer: False
language_model: Austism/chronos-hermes-13b
model_size: 13B
ranking_group: single
us_pacific_date: 2025-01-22
win_ratio: 0.4501358695652174
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, '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 austism-chronos-hermes-13b-v1-mkmlizer
Waiting for job on austism-chronos-hermes-13b-v1-mkmlizer to finish
austism-chronos-hermes-13b-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
austism-chronos-hermes-13b-v1-mkmlizer: ║     _____            __           __                                ║
austism-chronos-hermes-13b-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
austism-chronos-hermes-13b-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
austism-chronos-hermes-13b-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
austism-chronos-hermes-13b-v1-mkmlizer: ║       /___/                                                         ║
austism-chronos-hermes-13b-v1-mkmlizer: ║                                                                     ║
austism-chronos-hermes-13b-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
austism-chronos-hermes-13b-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
austism-chronos-hermes-13b-v1-mkmlizer: ║  https://mk1.ai                                                     ║
austism-chronos-hermes-13b-v1-mkmlizer: ║                                                                     ║
austism-chronos-hermes-13b-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
austism-chronos-hermes-13b-v1-mkmlizer: ║  belonging to:                                                      ║
austism-chronos-hermes-13b-v1-mkmlizer: ║                                                                     ║
austism-chronos-hermes-13b-v1-mkmlizer: ║  Chai Research Corp.                                                ║
austism-chronos-hermes-13b-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
austism-chronos-hermes-13b-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
austism-chronos-hermes-13b-v1-mkmlizer: ║                                                                     ║
austism-chronos-hermes-13b-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
austism-chronos-hermes-13b-v1-mkmlizer: Downloaded to shared memory in 82.776s
austism-chronos-hermes-13b-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt2stnaag, device:0
austism-chronos-hermes-13b-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
austism-chronos-hermes-13b-v1-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.
austism-chronos-hermes-13b-v1-mkmlizer:   tensors = torch.load(model_shard_filename, map_location=torch.device(self.device), mmap=True)
austism-chronos-hermes-13b-v1-mkmlizer: 
Loading 0:   0%|          | 0/403 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/403 [00:00<00:11, 34.66it/s]
Loading 0:   3%|▎         | 14/403 [00:00<00:06, 60.70it/s]
Loading 0:   6%|▌         | 24/403 [00:00<00:05, 70.47it/s]
Loading 0:   8%|▊         | 31/403 [00:00<00:14, 26.48it/s]
Loading 0:  10%|▉         | 39/403 [00:01<00:11, 31.56it/s]
Loading 0:  12%|█▏        | 49/403 [00:01<00:08, 39.85it/s]
Loading 0:  15%|█▍        | 59/403 [00:01<00:07, 46.70it/s]
Loading 0:  16%|█▌        | 65/403 [00:01<00:12, 26.47it/s]
Loading 0:  18%|█▊        | 74/403 [00:02<00:10, 32.80it/s]
Loading 0:  21%|██        | 84/403 [00:02<00:08, 39.87it/s]
Loading 0:  23%|██▎       | 94/403 [00:02<00:06, 46.28it/s]
Loading 0:  25%|██▍       | 100/403 [00:02<00:10, 27.72it/s]
Loading 0:  27%|██▋       | 109/403 [00:03<00:08, 34.04it/s]
Loading 0:  30%|██▉       | 119/403 [00:03<00:06, 40.69it/s]
Loading 0:  32%|███▏      | 127/403 [00:03<00:10, 26.81it/s]
Loading 0:  33%|███▎      | 134/403 [00:03<00:08, 30.01it/s]
Loading 0:  36%|███▌      | 144/403 [00:04<00:07, 36.97it/s]
Loading 0:  38%|███▊      | 154/403 [00:04<00:05, 43.32it/s]
Loading 0:  40%|███▉      | 160/403 [00:04<00:09, 25.65it/s]
Loading 0:  42%|████▏     | 169/403 [00:04<00:07, 31.51it/s]
Loading 0:  44%|████▍     | 179/403 [00:05<00:05, 38.32it/s]
Loading 0:  47%|████▋     | 189/403 [00:05<00:08, 26.56it/s]
Loading 0:  49%|████▉     | 199/403 [00:05<00:06, 32.80it/s]
Loading 0:  52%|█████▏    | 209/403 [00:06<00:04, 38.93it/s]
Loading 0:  54%|█████▍    | 219/403 [00:06<00:04, 44.63it/s]
Loading 0:  56%|█████▌    | 225/403 [00:06<00:06, 27.23it/s]
Loading 0:  58%|█████▊    | 234/403 [00:06<00:05, 33.06it/s]
Loading 0:  61%|██████    | 244/403 [00:06<00:03, 39.91it/s]
Loading 0:  63%|██████▎   | 254/403 [00:07<00:03, 45.51it/s]
Loading 0:  65%|██████▍   | 260/403 [00:07<00:05, 27.80it/s]
Loading 0:  67%|██████▋   | 269/403 [00:07<00:04, 33.39it/s]
Loading 0:  69%|██████▉   | 279/403 [00:07<00:03, 39.99it/s]
Loading 0:  71%|███████   | 287/403 [00:08<00:04, 27.88it/s]
Loading 0:  73%|███████▎  | 294/403 [00:08<00:03, 31.66it/s]
Loading 0:  75%|███████▌  | 304/403 [00:08<00:02, 38.90it/s]
Loading 0:  78%|███████▊  | 314/403 [00:08<00:02, 44.23it/s]
Loading 0:  79%|███████▉  | 320/403 [00:09<00:03, 27.61it/s]
Loading 0:  82%|████████▏ | 329/403 [00:09<00:02, 34.43it/s]
Loading 0:  84%|████████▍ | 339/403 [00:09<00:01, 42.39it/s]
Loading 0:  87%|████████▋ | 349/403 [00:10<00:01, 28.89it/s]
Loading 0:  89%|████████▉ | 359/403 [00:10<00:01, 35.44it/s]
Loading 0:  92%|█████████▏| 369/403 [00:10<00:00, 42.04it/s]
Loading 0:  94%|█████████▍| 379/403 [00:10<00:00, 47.17it/s]
Loading 0:  96%|█████████▌| 386/403 [00:11<00:00, 33.22it/s]
Loading 0:  98%|█████████▊| 394/403 [00:11<00:00, 37.57it/s]
Loading 0: 100%|██████████| 403/403 [00:12<00:00, 13.19it/s]
                                                            
You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message
austism-chronos-hermes-13b-v1-mkmlizer: You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 - if you loaded a llama tokenizer from a GGUF file you can ignore this message.
austism-chronos-hermes-13b-v1-mkmlizer: quantized model in 30.410s
austism-chronos-hermes-13b-v1-mkmlizer: Processed model Austism/chronos-hermes-13b in 113.186s
austism-chronos-hermes-13b-v1-mkmlizer: creating bucket guanaco-mkml-models
austism-chronos-hermes-13b-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
austism-chronos-hermes-13b-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/austism-chronos-hermes-13b-v1
austism-chronos-hermes-13b-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/austism-chronos-hermes-13b-v1/special_tokens_map.json
austism-chronos-hermes-13b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/austism-chronos-hermes-13b-v1/tokenizer_config.json
austism-chronos-hermes-13b-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/austism-chronos-hermes-13b-v1/config.json
austism-chronos-hermes-13b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/austism-chronos-hermes-13b-v1/tokenizer.model
austism-chronos-hermes-13b-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/austism-chronos-hermes-13b-v1/tokenizer.json
austism-chronos-hermes-13b-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/austism-chronos-hermes-13b-v1/flywheel_model.0.safetensors
Job austism-chronos-hermes-13b-v1-mkmlizer completed after 135.55s with status: succeeded
Stopping job with name austism-chronos-hermes-13b-v1-mkmlizer
Pipeline stage MKMLizer completed in 135.99s
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 austism-chronos-hermes-13b-v1
Waiting for inference service austism-chronos-hermes-13b-v1 to be ready
Inference service austism-chronos-hermes-13b-v1 ready after 140.50312900543213s
Pipeline stage MKMLDeployer completed in 141.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4318995475769043s
Received healthy response to inference request in 2.1793010234832764s
Received healthy response to inference request in 2.1245224475860596s
Received healthy response to inference request in 2.081942558288574s
Received healthy response to inference request in 2.10830020904541s
5 requests
0 failed requests
5th percentile: 2.0872140884399415
10th percentile: 2.0924856185913088
20th percentile: 2.103028678894043
30th percentile: 2.11154465675354
40th percentile: 2.1180335521697997
50th percentile: 2.1245224475860596
60th percentile: 2.146433877944946
70th percentile: 2.168345308303833
80th percentile: 2.229820728302002
90th percentile: 2.330860137939453
95th percentile: 2.3813798427581787
99th percentile: 2.421795606613159
mean time: 2.185193157196045
Pipeline stage StressChecker completed in 12.07s
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 0.61s
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
austism-chronos-hermes-13b_v1 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 5367.58s
Shutdown handler de-registered
austism-chronos-hermes-13b_v1 status is now inactive due to auto deactivation removed underperforming models
austism-chronos-hermes-13b_v1 status is now torndown due to DeploymentManager action