submission_id: nitral-ai-hathor-l3-8b-v-01_v9
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/Hathor-L3-8B-v.01
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{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: 2024-06-22T20:48:43+00:00
model_name: nitral-ai-hathor-l3-8b-v01
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 21595
num_wins: 11323
celo_rating: 1216.49
propriety_score: 0.7169309657202545
propriety_total_count: 10531.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v01
ineligible_reason: None
language_model: Nitral-AI/Hathor-L3-8B-v.01
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.5243343366520028
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v9-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.
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:51, 2.26s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.42it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:21, 11.73it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.15it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.76it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.95it/s] Loading 0: 33%|███▎ | 97/291 [00:05<00:03, 50.04it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.93it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 80.14it/s] Loading 0: 51%|█████ | 149/291 [00:05<00:01, 97.21it/s] Loading 0: 57%|█████▋ | 166/291 [00:06<00:01, 74.86it/s] Loading 0: 63%|██████▎ | 184/291 [00:06<00:01, 91.30it/s] Loading 0: 69%|██████▉ | 202/291 [00:06<00:00, 107.04it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 120.73it/s] Loading 0: 82%|████████▏ | 238/291 [00:06<00:00, 132.05it/s] Loading 0: 88%|████████▊ | 256/291 [00:06<00:00, 142.04it/s] Loading 0: 94%|█████████▍| 273/291 [00:06<00:00, 92.74it/s] Loading 0: 99%|█████████▉| 288/291 [00:06<00:00, 102.75it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: quantized model in 23.024s
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 52.310s
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v9
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v9/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v9/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v9/config.json
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v9/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v9/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-01-v9-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.
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v9-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.
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v9-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.
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v9-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()
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: Saving duration: 0.387s
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.162s
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v9_reward
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v9_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v9_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v9_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v9_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v9_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v9_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v9_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer completed after 83.24s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v9-mkmlizer
Pipeline stage MKMLizer completed in 83.64s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-01-v9
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v9 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v9 ready after 130.57156491279602s
Pipeline stage ISVCDeployer completed in 136.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1757750511169434s
Received healthy response to inference request in 1.3934667110443115s
Received healthy response to inference request in 1.458617925643921s
Received healthy response to inference request in 1.2517197132110596s
Received healthy response to inference request in 1.3182716369628906s
5 requests
0 failed requests
5th percentile: 1.2650300979614257
10th percentile: 1.278340482711792
20th percentile: 1.3049612522125245
30th percentile: 1.3333106517791748
40th percentile: 1.363388681411743
50th percentile: 1.3934667110443115
60th percentile: 1.4195271968841552
70th percentile: 1.445587682723999
80th percentile: 1.6020493507385256
90th percentile: 1.8889122009277344
95th percentile: 2.032343626022339
99th percentile: 2.1470887660980225
mean time: 1.5195702075958253
Pipeline stage StressChecker completed in 8.30s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
nitral-ai-hathor-l3-8b-v-01_v9 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v9 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics