submission_id: nitral-ai-hathor-l3-8b-v-02_v11
developer_uid: Nitral-AI
status: inactive
model_repo: Nitral-AI/Hathor-L3-8B-v.02
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 45, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|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: 2024-06-22T20:04:15+00:00
model_name: nitral-ai-hathor-l3-8b-v02
model_group: Nitral-AI/Hathor-L3-8B-v
num_battles: 17654
num_wins: 9287
celo_rating: 1217.44
propriety_score: 0.7173754556500608
propriety_total_count: 8230.0
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-v02
ineligible_reason: None
language_model: Nitral-AI/Hathor-L3-8B-v.02
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-06-22
win_ratio: 0.5260564178089951
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer
Waiting for job on nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer to finish
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ _____ __ __ ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ /___/ ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ Version: 0.8.14 ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ https://mk1.ai ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ The license key for the current software has been verified as ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ belonging to: ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ Chai Research Corp. ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ║ ║
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nitral-ai-hathor-l3-8b-v-02-v11-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-02-v11-mkmlizer: warnings.warn(warning_message, FutureWarning)
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: Downloaded to shared memory in 36.450s
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: quantizing model to /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<10:52, 2.26s/it] Loading 0: 5%|▌ | 15/291 [00:04<01:02, 4.41it/s] Loading 0: 11%|█▏ | 33/291 [00:04<00:22, 11.70it/s] Loading 0: 18%|█▊ | 51/291 [00:04<00:11, 21.06it/s] Loading 0: 22%|██▏ | 65/291 [00:05<00:08, 25.50it/s] Loading 0: 28%|██▊ | 81/291 [00:05<00:05, 36.55it/s] Loading 0: 33%|███▎ | 96/291 [00:05<00:04, 48.27it/s] Loading 0: 39%|███▉ | 114/291 [00:05<00:02, 64.93it/s] Loading 0: 45%|████▌ | 131/291 [00:05<00:01, 80.55it/s] Loading 0: 50%|█████ | 146/291 [00:05<00:01, 87.54it/s] Loading 0: 55%|█████▍ | 160/291 [00:05<00:01, 94.26it/s] Loading 0: 60%|█████▉ | 174/291 [00:06<00:01, 71.43it/s] Loading 0: 64%|██████▍ | 186/291 [00:06<00:01, 79.46it/s] Loading 0: 70%|███████ | 204/291 [00:06<00:00, 97.00it/s] Loading 0: 76%|███████▋ | 222/291 [00:06<00:00, 111.82it/s] Loading 0: 82%|████████▏ | 240/291 [00:06<00:00, 123.88it/s] Loading 0: 89%|████████▊ | 258/291 [00:06<00:00, 133.09it/s] Loading 0: 94%|█████████▍| 273/291 [00:07<00:00, 91.11it/s] Loading 0: 98%|█████████▊| 285/291 [00:07<00:00, 96.44it/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-02-v11-mkmlizer: quantized model in 23.191s
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: Processed model Nitral-AI/Hathor-L3-8B-v.02 in 62.140s
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: creating bucket guanaco-mkml-models
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v11
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v11/config.json
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v11/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v11/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v11/tokenizer.json
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nitral-ai-hathor-l3-8b-v-02-v11/flywheel_model.0.safetensors
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
nitral-ai-hathor-l3-8b-v-02-v11-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-02-v11-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v11-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-02-v11-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v11-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-02-v11-mkmlizer: warnings.warn(
nitral-ai-hathor-l3-8b-v-02-v11-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-02-v11-mkmlizer: return self.fget.__get__(instance, owner)()
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: Saving duration: 0.396s
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.780s
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: creating bucket guanaco-reward-models
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v11_reward
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v11_reward/config.json
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v11_reward/special_tokens_map.json
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v11_reward/tokenizer_config.json
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v11_reward/merges.txt
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v11_reward/vocab.json
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v11_reward/tokenizer.json
nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nitral-ai-hathor-l3-8b-v-02-v11_reward/reward.tensors
Job nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer completed after 93.49s with status: succeeded
Stopping job with name nitral-ai-hathor-l3-8b-v-02-v11-mkmlizer
Pipeline stage MKMLizer completed in 93.97s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service nitral-ai-hathor-l3-8b-v-02-v11
Waiting for inference service nitral-ai-hathor-l3-8b-v-02-v11 to be ready
Inference service nitral-ai-hathor-l3-8b-v-02-v11 ready after 40.372907876968384s
Pipeline stage ISVCDeployer completed in 46.05s
Running pipeline stage StressChecker
%s, retrying in %s seconds...
Received healthy response to inference request in 1.6499109268188477s
Received healthy response to inference request in 1.3427934646606445s
Received healthy response to inference request in 1.306246042251587s
Received healthy response to inference request in 1.2721526622772217s
Received healthy response to inference request in 1.3437018394470215s
5 requests
0 failed requests
5th percentile: 1.2789713382720946
10th percentile: 1.2857900142669678
20th percentile: 1.299427366256714
30th percentile: 1.3135555267333985
40th percentile: 1.3281744956970214
50th percentile: 1.3427934646606445
60th percentile: 1.3431568145751953
70th percentile: 1.343520164489746
80th percentile: 1.4049436569213867
90th percentile: 1.5274272918701173
95th percentile: 1.5886691093444825
99th percentile: 1.6376625633239745
mean time: 1.3829609870910644
Pipeline stage StressChecker completed in 27.72s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
nitral-ai-hathor-l3-8b-v-02_v11 status is now deployed due to DeploymentManager action
nitral-ai-hathor-l3-8b-v-02_v11 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics