submission_id: hyperblaze-l3-8b-soliloq_2337_v4
developer_uid: HyperBlaze
status: inactive
model_repo: HyperBlaze/L3-8B-Soliloquy-v2-SpicyMaid-Lewd-Mergetest
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.95, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.7, 'frequency_penalty': 0.1, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '<|start_header_id|>system<|end_header_id|>\n\nYou are `{bot_name}` and engage in a Roleplay with `{user_name}`.\n\n Your next response, will be based on action and dialogue based on the provided context.\n\n Your persona as {bot_name}: {memory}\n', 'prompt_template': 'Your example message as {bot_name}: {prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
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}:', 'truncate_by_message': False}
timestamp: 2024-05-08T23:25:33+00:00
model_name: soliloquyv2-mergepromptfix
model_eval_status: success
double_thumbs_up: 173
thumbs_up: 275
thumbs_down: 145
num_battles: 14323
num_wins: 7554
celo_rating: 1194.45
entertaining: 7.38
stay_in_character: 8.85
user_preference: 7.46
safety_score: 0.97
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: soliloquyv2-mergepromptfix
double_thumbs_up_ratio: 0.2917369308600337
feedback_count: 593
ineligible_reason: None
language_model: HyperBlaze/L3-8B-Soliloquy-v2-SpicyMaid-Lewd-Mergetest
model_score: 7.896666666666667
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.463743676222597
thumbs_down_ratio: 0.24451939291736932
thumbs_up_ratio: 0.7554806070826307
us_pacific_date: 2024-05-08
win_ratio: 0.5274034769252252
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer
Waiting for job on hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer to finish
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ _____ __ __ ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ /___/ ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ Version: 0.8.10 ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ The license key for the current software has been verified as ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ belonging to: ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ Chai Research Corp. ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ║ ║
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: Downloaded to shared memory in 12.869s
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: quantizing model to /dev/shm/model_cache
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 35%|███▌ | 103/291 [00:01<00:01, 102.11it/s] Loading 0: 64%|██████▍ | 187/291 [00:07<00:04, 20.82it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: quantized model in 21.162s
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: Processed model HyperBlaze/L3-8B-Soliloquy-v2-SpicyMaid-Lewd-Mergetest in 35.400s
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: creating bucket guanaco-mkml-models
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v4
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v4/special_tokens_map.json
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v4/tokenizer_config.json
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v4/config.json
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v4/tokenizer.json
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hyperblaze-l3-8b-soliloq-2337-v4/flywheel_model.0.safetensors
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: warnings.warn(
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: warnings.warn(
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: warnings.warn(
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: return self.fget.__get__(instance, owner)()
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: Saving duration: 0.262s
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.529s
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: creating bucket guanaco-reward-models
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v4_reward
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v4_reward/special_tokens_map.json
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v4_reward/config.json
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v4_reward/tokenizer_config.json
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v4_reward/merges.txt
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v4_reward/vocab.json
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v4_reward/tokenizer.json
hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hyperblaze-l3-8b-soliloq-2337-v4_reward/reward.tensors
Job hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer completed after 63.5s with status: succeeded
Stopping job with name hyperblaze-l3-8b-soliloq-2337-v4-mkmlizer
Pipeline stage MKMLizer completed in 65.72s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hyperblaze-l3-8b-soliloq-2337-v4
Waiting for inference service hyperblaze-l3-8b-soliloq-2337-v4 to be ready
Inference service hyperblaze-l3-8b-soliloq-2337-v4 ready after 40.27018475532532s
Pipeline stage ISVCDeployer completed in 47.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1227869987487793s
Received healthy response to inference request in 1.1884346008300781s
Received healthy response to inference request in 1.1860225200653076s
Received healthy response to inference request in 1.1651489734649658s
Received healthy response to inference request in 1.1867399215698242s
5 requests
0 failed requests
5th percentile: 1.1693236827850342
10th percentile: 1.1734983921051025
20th percentile: 1.1818478107452393
30th percentile: 1.186166000366211
40th percentile: 1.1864529609680177
50th percentile: 1.1867399215698242
60th percentile: 1.1874177932739258
70th percentile: 1.1880956649780274
80th percentile: 1.3753050804138185
90th percentile: 1.749046039581299
95th percentile: 1.935916519165039
99th percentile: 2.085412902832031
mean time: 1.369826602935791
Pipeline stage StressChecker completed in 7.37s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
M-Eval Dataset for topic stay_in_character is loaded
hyperblaze-l3-8b-soliloq_2337_v4 status is now deployed due to DeploymentManager action
hyperblaze-l3-8b-soliloq_2337_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics