submission_id: neversleep-llama-3-lumim_7274_v1
developer_uid: robert_irvine
status: inactive
model_repo: NeverSleep/Llama-3-Lumimaid-8B-v0.1
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\nThis is an entertaining conversation. You are {bot_name} who has persona: {memory}. Engage in a chat with {user_name} while staying in character. Try to flirt with {user_name}. Engage in *roleplay* actions. Describe the scene dramatically<|eot_id|>', 'prompt_template': '<|start_header_id|>system<|end_header_id|>\n\nExample 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: 2024-05-02T16:50:54+00:00
model_name: neversleep-llama-3-lumim_7274_v1
model_eval_status: pending
double_thumbs_up: 75
thumbs_up: 122
thumbs_down: 56
num_battles: 9256
num_wins: 4419
celo_rating: 1147.91
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: neversleep-llama-3-lumim_7274_v1
double_thumbs_up_ratio: 0.2964426877470356
feedback_count: 253
ineligible_reason: None
language_model: NeverSleep/Llama-3-Lumimaid-8B-v0.1
model_score: None
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.48221343873517786
thumbs_down_ratio: 0.22134387351778656
thumbs_up_ratio: 0.7786561264822134
us_pacific_date: 2024-05-02
win_ratio: 0.4774200518582541
Resubmit model
Running pipeline stage MKMLizer
Starting job with name neversleep-llama-3-lumim-7274-v1-mkmlizer
Waiting for job on neversleep-llama-3-lumim-7274-v1-mkmlizer to finish
neversleep-llama-3-lumim-7274-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ _____ __ __ ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ /___/ ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ Version: 0.8.10 ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ The license key for the current software has been verified as ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ belonging to: ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ Chai Research Corp. ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ║ ║
neversleep-llama-3-lumim-7274-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
neversleep-llama-3-lumim-7274-v1-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.
neversleep-llama-3-lumim-7274-v1-mkmlizer: warnings.warn(warning_message, FutureWarning)
neversleep-llama-3-lumim-7274-v1-mkmlizer: Downloaded to shared memory in 17.296s
neversleep-llama-3-lumim-7274-v1-mkmlizer: quantizing model to /dev/shm/model_cache
neversleep-llama-3-lumim-7274-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
neversleep-llama-3-lumim-7274-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:03<09:32, 1.98s/it] Loading 0: 57%|█████▋ | 166/291 [00:05<00:03, 41.15it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
neversleep-llama-3-lumim-7274-v1-mkmlizer: quantized model in 16.775s
neversleep-llama-3-lumim-7274-v1-mkmlizer: Processed model NeverSleep/Llama-3-Lumimaid-8B-v0.1 in 35.008s
neversleep-llama-3-lumim-7274-v1-mkmlizer: creating bucket guanaco-mkml-models
neversleep-llama-3-lumim-7274-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
neversleep-llama-3-lumim-7274-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v1
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v1/special_tokens_map.json
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v1/tokenizer_config.json
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v1/config.json
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v1/tokenizer.json
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/neversleep-llama-3-lumim-7274-v1/flywheel_model.0.safetensors
neversleep-llama-3-lumim-7274-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
neversleep-llama-3-lumim-7274-v1-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.
neversleep-llama-3-lumim-7274-v1-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-7274-v1-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.
neversleep-llama-3-lumim-7274-v1-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-7274-v1-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.
neversleep-llama-3-lumim-7274-v1-mkmlizer: warnings.warn(
neversleep-llama-3-lumim-7274-v1-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()
neversleep-llama-3-lumim-7274-v1-mkmlizer: return self.fget.__get__(instance, owner)()
neversleep-llama-3-lumim-7274-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
neversleep-llama-3-lumim-7274-v1-mkmlizer: Saving duration: 0.254s
neversleep-llama-3-lumim-7274-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.867s
neversleep-llama-3-lumim-7274-v1-mkmlizer: creating bucket guanaco-reward-models
neversleep-llama-3-lumim-7274-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
neversleep-llama-3-lumim-7274-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v1_reward
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v1_reward/config.json
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v1_reward/special_tokens_map.json
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v1_reward/tokenizer_config.json
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v1_reward/merges.txt
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v1_reward/vocab.json
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v1_reward/tokenizer.json
neversleep-llama-3-lumim-7274-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/neversleep-llama-3-lumim-7274-v1_reward/reward.tensors
Job neversleep-llama-3-lumim-7274-v1-mkmlizer completed after 68.52s with status: succeeded
Stopping job with name neversleep-llama-3-lumim-7274-v1-mkmlizer
Pipeline stage MKMLizer completed in 69.83s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.31s
Running pipeline stage ISVCDeployer
Creating inference service neversleep-llama-3-lumim-7274-v1
Waiting for inference service neversleep-llama-3-lumim-7274-v1 to be ready
Inference service neversleep-llama-3-lumim-7274-v1 ready after 40.475332260131836s
Pipeline stage ISVCDeployer completed in 46.70s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9868946075439453s
Received healthy response to inference request in 1.32924222946167s
Received healthy response to inference request in 1.214841365814209s
Received healthy response to inference request in 1.2547695636749268s
Received healthy response to inference request in 1.232154130935669s
5 requests
0 failed requests
5th percentile: 1.218303918838501
10th percentile: 1.221766471862793
20th percentile: 1.228691577911377
30th percentile: 1.2366772174835206
40th percentile: 1.2457233905792235
50th percentile: 1.2547695636749268
60th percentile: 1.2845586299896241
70th percentile: 1.3143476963043212
80th percentile: 1.4607727050781252
90th percentile: 1.7238336563110352
95th percentile: 1.85536413192749
99th percentile: 1.9605885124206544
mean time: 1.403580379486084
Pipeline stage StressChecker completed in 9.60s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.10s
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 0.23s
%s, retrying in %s seconds...
neversleep-llama-3-lumim_7274_v1 status is now deployed due to DeploymentManager action
%s, retrying in %s seconds...
neversleep-llama-3-lumim_7274_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics