submission_id: nitral-ai-hathor-l3-8b-v-01_v8
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': 0.01, 'top_k': 45, '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: 2024-06-20T15:17:44+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 23394
num_wins: 12797
celo_rating: 1216.82
propriety_score: 0.7066068443740653
propriety_total_count: 11367.0
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-v-01_v1
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: 2024-06-20
win_ratio: 0.5470206035735659
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-01-v8-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-v8-mkmlizer: warnings.warn(warning_message, FutureWarning)
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: Downloaded to shared memory in 42.242s
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:15, 2.13s/it] Loading 0: 5%|▌ | 15/291 [00:04<00:59, 4.65it/s] Loading 0: 11%|█ | 32/291 [00:04<00:21, 11.92it/s] Loading 0: 17%|█▋ | 49/291 [00:04<00:11, 21.18it/s] Loading 0: 21%|██▏ | 62/291 [00:05<00:09, 23.14it/s] Loading 0: 26%|██▋ | 77/291 [00:05<00:06, 33.16it/s] Loading 0: 32%|███▏ | 94/291 [00:05<00:04, 46.78it/s] Loading 0: 37%|███▋ | 109/291 [00:05<00:03, 59.50it/s] Loading 0: 42%|████▏ | 123/291 [00:05<00:02, 70.57it/s] Loading 0: 48%|████▊ | 140/291 [00:05<00:01, 87.50it/s] Loading 0: 54%|█████▍ | 157/291 [00:05<00:01, 103.81it/s] Loading 0: 59%|█████▉ | 172/291 [00:06<00:01, 62.11it/s] Loading 0: 64%|██████▍ | 186/291 [00:06<00:01, 72.33it/s] Loading 0: 70%|██████▉ | 203/291 [00:06<00:00, 88.28it/s] Loading 0: 76%|███████▌ | 220/291 [00:06<00:00, 103.20it/s] Loading 0: 81%|████████ | 235/291 [00:06<00:00, 112.37it/s] Loading 0: 86%|████████▌ | 250/291 [00:06<00:00, 118.37it/s] Loading 0: 91%|█████████▏| 266/291 [00:07<00:00, 68.96it/s] Loading 0: 97%|█████████▋| 283/291 [00:07<00:00, 84.49it/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-v8-mkmlizer: quantized model in 20.066s
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.01 in 63.422s
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v8
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v8/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v8/config.json
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v8/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v8/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-01-v8/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-01-v8-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-v8-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v8-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-v8-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v8-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-v8-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-01-v8-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-v8-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: Saving duration: 0.305s
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.158s
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v8_reward/config.json
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v8_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v8_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v8_reward/merges.txt
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v8_reward/vocab.json
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v8_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-01-v8_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer completed after 95.72s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-01-v8-mkmlizer
Pipeline stage MKMLizer completed in 99.83s
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-v8
Waiting for inference service nitral-ai-hathor-l3-8b-v-01-v8 to be ready
Inference service nitral-ai-hathor-l3-8b-v-01-v8 ready after 50.324963092803955s
Pipeline stage ISVCDeployer completed in 57.57s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2009334564208984s
Received healthy response to inference request in 1.347339153289795s
Received healthy response to inference request in 1.3006174564361572s
Received healthy response to inference request in 1.258441686630249s
Received healthy response to inference request in 1.348198413848877s
5 requests
0 failed requests
5th percentile: 1.2668768405914306
10th percentile: 1.2753119945526123
20th percentile: 1.2921823024749757
30th percentile: 1.3099617958068848
40th percentile: 1.3286504745483398
50th percentile: 1.347339153289795
60th percentile: 1.3476828575134276
70th percentile: 1.3480265617370606
80th percentile: 1.5187454223632815
90th percentile: 1.8598394393920898
95th percentile: 2.030386447906494
99th percentile: 2.1668240547180178
mean time: 1.4911060333251953
Pipeline stage StressChecker completed in 8.35s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.04s
nitral-ai-hathor-l3-8b-v-01_v8 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-01_v8 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics