submission_id: undi95-llama-3-lewdplay-_3862_v4
developer_uid: robert_irvine
status: inactive
model_repo: Undi95/Llama-3-LewdPlay-8B-evo
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|start_header_id|>', '\n\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nDescription: {memory}", 'prompt_template': 'Example conversation:\n{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': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
timestamp: 2024-05-02T17:02:55+00:00
model_name: undi95-llama-3-lewdplay-_3862_v4
model_eval_status: pending
double_thumbs_up: 214
thumbs_up: 287
thumbs_down: 166
num_battles: 21227
num_wins: 10125
celo_rating: 1146.07
entertaining: None
stay_in_character: None
user_preference: None
safety_score: None
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: undi95-llama-3-lewdplay-_3862_v4
double_thumbs_up_ratio: 0.32083958020989506
feedback_count: 667
ineligible_reason: None
language_model: Undi95/Llama-3-LewdPlay-8B-evo
model_score: None
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4302848575712144
thumbs_down_ratio: 0.24887556221889057
thumbs_up_ratio: 0.7511244377811095
us_pacific_date: 2024-05-02
win_ratio: 0.47698685636218024
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-llama-3-lewdplay-3862-v4-mkmlizer
Waiting for job on undi95-llama-3-lewdplay-3862-v4-mkmlizer to finish
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ _____ __ __ ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ /___/ ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ Version: 0.8.10 ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ The license key for the current software has been verified as ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ belonging to: ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ Chai Research Corp. ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ║ ║
undi95-llama-3-lewdplay-3862-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
undi95-llama-3-lewdplay-3862-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.
undi95-llama-3-lewdplay-3862-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
undi95-llama-3-lewdplay-3862-v4-mkmlizer: Downloaded to shared memory in 16.557s
undi95-llama-3-lewdplay-3862-v4-mkmlizer: quantizing model to /dev/shm/model_cache
undi95-llama-3-lewdplay-3862-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
undi95-llama-3-lewdplay-3862-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<09:51, 2.05s/it] Loading 0: 57%|█████▋ | 166/291 [00:05<00:03, 40.28it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
undi95-llama-3-lewdplay-3862-v4-mkmlizer: quantized model in 16.983s
undi95-llama-3-lewdplay-3862-v4-mkmlizer: Processed model Undi95/Llama-3-LewdPlay-8B-evo in 34.430s
undi95-llama-3-lewdplay-3862-v4-mkmlizer: creating bucket guanaco-mkml-models
undi95-llama-3-lewdplay-3862-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-llama-3-lewdplay-3862-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v4
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v4/tokenizer_config.json
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v4/config.json
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v4/special_tokens_map.json
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v4/tokenizer.json
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-llama-3-lewdplay-3862-v4/flywheel_model.0.safetensors
undi95-llama-3-lewdplay-3862-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.
undi95-llama-3-lewdplay-3862-v4-mkmlizer: warnings.warn(
undi95-llama-3-lewdplay-3862-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.
undi95-llama-3-lewdplay-3862-v4-mkmlizer: warnings.warn(
undi95-llama-3-lewdplay-3862-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()
undi95-llama-3-lewdplay-3862-v4-mkmlizer: return self.fget.__get__(instance, owner)()
undi95-llama-3-lewdplay-3862-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-llama-3-lewdplay-3862-v4-mkmlizer: Saving duration: 0.236s
undi95-llama-3-lewdplay-3862-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 7.876s
undi95-llama-3-lewdplay-3862-v4-mkmlizer: creating bucket guanaco-reward-models
undi95-llama-3-lewdplay-3862-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-llama-3-lewdplay-3862-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v4_reward
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v4_reward/config.json
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v4_reward/tokenizer_config.json
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v4_reward/vocab.json
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v4_reward/merges.txt
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v4_reward/special_tokens_map.json
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v4_reward/tokenizer.json
undi95-llama-3-lewdplay-3862-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-llama-3-lewdplay-3862-v4_reward/reward.tensors
Job undi95-llama-3-lewdplay-3862-v4-mkmlizer completed after 68.19s with status: succeeded
Stopping job with name undi95-llama-3-lewdplay-3862-v4-mkmlizer
Pipeline stage MKMLizer completed in 69.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.29s
Running pipeline stage ISVCDeployer
Creating inference service undi95-llama-3-lewdplay-3862-v4
Waiting for inference service undi95-llama-3-lewdplay-3862-v4 to be ready
Inference service undi95-llama-3-lewdplay-3862-v4 ready after 40.5815110206604s
Pipeline stage ISVCDeployer completed in 46.90s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.97251558303833s
Received healthy response to inference request in 1.2835772037506104s
Received healthy response to inference request in 1.1692965030670166s
Received healthy response to inference request in 1.1856632232666016s
Received healthy response to inference request in 1.2544026374816895s
5 requests
0 failed requests
5th percentile: 1.1725698471069337
10th percentile: 1.1758431911468505
20th percentile: 1.1823898792266845
30th percentile: 1.199411106109619
40th percentile: 1.2269068717956544
50th percentile: 1.2544026374816895
60th percentile: 1.2660724639892578
70th percentile: 1.277742290496826
80th percentile: 1.4213648796081544
90th percentile: 1.6969402313232422
95th percentile: 1.834727907180786
99th percentile: 1.9449580478668214
mean time: 1.3730910301208497
Pipeline stage StressChecker completed in 9.02s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.09s
Running M-Eval for topic stay_in_character
Running pipeline stage DaemonicSafetyScorer
M-Eval Dataset for topic stay_in_character is loaded
Pipeline stage DaemonicSafetyScorer completed in 0.25s
%s, retrying in %s seconds...
undi95-llama-3-lewdplay-_3862_v4 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
Scoring model output for bot %s
undi95-llama-3-lewdplay-_3862_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics