submission_id: undi95-llama-3-unholy-8b_v4
developer_uid: Meliodia
status: inactive
model_repo: Undi95/Llama-3-Unholy-8B
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, '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}
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: 2024-04-29T19:13:31+00:00
model_name: Undi95Llama-3-Unholy-8B
model_eval_status: success
double_thumbs_up: 74
thumbs_up: 149
thumbs_down: 97
num_battles: 7289
num_wins: 3807
celo_rating: 1174.12
entertaining: 7.0
stay_in_character: 8.65
user_preference: 7.4
safety_score: 0.92
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: Undi95Llama-3-Unholy-8B
double_thumbs_up_ratio: 0.23125
feedback_count: 320
ineligible_reason: None
language_model: Undi95/Llama-3-Unholy-8B
model_score: 7.683333333333334
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.465625
thumbs_down_ratio: 0.303125
thumbs_up_ratio: 0.696875
us_pacific_date: 2024-04-29
win_ratio: 0.5222938674715324
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-llama-3-unholy-8b-v4-mkmlizer
Waiting for job on undi95-llama-3-unholy-8b-v4-mkmlizer to finish
undi95-llama-3-unholy-8b-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ _____ __ __ ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ /___/ ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ Version: 0.8.10 ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ The license key for the current software has been verified as ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ belonging to: ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ Chai Research Corp. ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ║ ║
undi95-llama-3-unholy-8b-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
undi95-llama-3-unholy-8b-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-unholy-8b-v4-mkmlizer: warnings.warn(warning_message, FutureWarning)
undi95-llama-3-unholy-8b-v4-mkmlizer: Downloaded to shared memory in 25.274s
undi95-llama-3-unholy-8b-v4-mkmlizer: quantizing model to /dev/shm/model_cache
undi95-llama-3-unholy-8b-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
undi95-llama-3-unholy-8b-v4-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 34%|███▎ | 98/291 [00:01<00:01, 97.95it/s] Loading 0: 72%|███████▏ | 210/291 [00:02<00:00, 105.40it/s] Loading 0: 99%|█████████▊| 287/291 [00:07<00:00, 30.52it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
undi95-llama-3-unholy-8b-v4-mkmlizer: quantized model in 18.895s
undi95-llama-3-unholy-8b-v4-mkmlizer: Processed model Undi95/Llama-3-Unholy-8B in 45.208s
undi95-llama-3-unholy-8b-v4-mkmlizer: creating bucket guanaco-mkml-models
undi95-llama-3-unholy-8b-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-llama-3-unholy-8b-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v4
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v4/special_tokens_map.json
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v4/config.json
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v4/tokenizer_config.json
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v4/tokenizer.json
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-llama-3-unholy-8b-v4/flywheel_model.0.safetensors
undi95-llama-3-unholy-8b-v4-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
undi95-llama-3-unholy-8b-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.
undi95-llama-3-unholy-8b-v4-mkmlizer: warnings.warn(
undi95-llama-3-unholy-8b-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-unholy-8b-v4-mkmlizer: warnings.warn(
undi95-llama-3-unholy-8b-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-unholy-8b-v4-mkmlizer: warnings.warn(
undi95-llama-3-unholy-8b-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-unholy-8b-v4-mkmlizer: return self.fget.__get__(instance, owner)()
undi95-llama-3-unholy-8b-v4-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-llama-3-unholy-8b-v4-mkmlizer: Saving duration: 0.291s
undi95-llama-3-unholy-8b-v4-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 9.883s
undi95-llama-3-unholy-8b-v4-mkmlizer: creating bucket guanaco-reward-models
undi95-llama-3-unholy-8b-v4-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-llama-3-unholy-8b-v4-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v4_reward
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v4_reward/config.json
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v4_reward/special_tokens_map.json
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v4_reward/tokenizer_config.json
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v4_reward/merges.txt
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v4_reward/vocab.json
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v4_reward/tokenizer.json
undi95-llama-3-unholy-8b-v4-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-llama-3-unholy-8b-v4_reward/reward.tensors
Job undi95-llama-3-unholy-8b-v4-mkmlizer completed after 73.88s with status: succeeded
Stopping job with name undi95-llama-3-unholy-8b-v4-mkmlizer
Pipeline stage MKMLizer completed in 76.85s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service undi95-llama-3-unholy-8b-v4
Waiting for inference service undi95-llama-3-unholy-8b-v4 to be ready
Inference service undi95-llama-3-unholy-8b-v4 ready after 40.274797201156616s
Pipeline stage ISVCDeployer completed in 47.53s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0869431495666504s
Received healthy response to inference request in 1.3039615154266357s
Received healthy response to inference request in 1.2887506484985352s
Received healthy response to inference request in 1.2590606212615967s
Received healthy response to inference request in 1.2682511806488037s
5 requests
0 failed requests
5th percentile: 1.260898733139038
10th percentile: 1.2627368450164795
20th percentile: 1.2664130687713624
30th percentile: 1.27235107421875
40th percentile: 1.2805508613586425
50th percentile: 1.2887506484985352
60th percentile: 1.2948349952697753
70th percentile: 1.3009193420410157
80th percentile: 1.4605578422546388
90th percentile: 1.7737504959106447
95th percentile: 1.9303468227386473
99th percentile: 2.05562388420105
mean time: 1.4413934230804444
Pipeline stage StressChecker completed in 7.81s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.04s
Running pipeline stage DaemonicSafetyScorer
Running M-Eval for topic stay_in_character
Pipeline stage DaemonicSafetyScorer completed in 0.04s
M-Eval Dataset for topic stay_in_character is loaded
undi95-llama-3-unholy-8b_v4 status is now deployed due to DeploymentManager action
undi95-llama-3-unholy-8b_v4 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics