submission_id: maldv-spring-chicken-8x8b_v7
developer_uid: maldevide
status: inactive
model_repo: maldv/spring-chicken-8x8b
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.1, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are {bot_name}. The following is a transcript of a conversation you had with {user_name}.\n\nMemory: {memory}', 'prompt_template': '\n\n{prompt}\n\nYou have a short, two sentence response.<|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: 2024-05-06T21:17:28+00:00
model_name: maldv-spring-chicken-8x8b_v1
model_eval_status: success
double_thumbs_up: 668
thumbs_up: 1031
thumbs_down: 475
num_battles: 52036
num_wins: 26379
celo_rating: 1182.76
entertaining: 7.4
stay_in_character: 8.58
user_preference: 7.5
safety_score: 0.93
submission_type: basic
model_architecture: MixtralForCausalLM
model_num_parameters: 47491321856.0
best_of: 8
max_input_tokens: 512
max_output_tokens: 64
display_name: maldv-spring-chicken-8x8b_v1
double_thumbs_up_ratio: 0.30726770929162833
feedback_count: 2174
ineligible_reason: None
language_model: maldv/spring-chicken-8x8b
model_score: 7.826666666666667
model_size: 47B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
single_thumbs_up_ratio: 0.4742410303587857
thumbs_down_ratio: 0.21849126034958602
thumbs_up_ratio: 0.781508739650414
us_pacific_date: 2024-05-06
win_ratio: 0.5069375048043662
Resubmit model
Running pipeline stage MKMLizer
Starting job with name maldv-spring-chicken-8x8b-v7-mkmlizer
Waiting for job on maldv-spring-chicken-8x8b-v7-mkmlizer to finish
maldv-spring-chicken-8x8b-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ _____ __ __ ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ /___/ ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ Version: 0.8.10 ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ The license key for the current software has been verified as ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ belonging to: ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ Chai Research Corp. ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ║ ║
maldv-spring-chicken-8x8b-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
maldv-spring-chicken-8x8b-v7-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.
maldv-spring-chicken-8x8b-v7-mkmlizer: warnings.warn(warning_message, FutureWarning)
maldv-spring-chicken-8x8b-v7-mkmlizer: Downloaded to shared memory in 77.377s
maldv-spring-chicken-8x8b-v7-mkmlizer: quantizing model to /dev/shm/model_cache
maldv-spring-chicken-8x8b-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
maldv-spring-chicken-8x8b-v7-mkmlizer: Loading 0: 0%| | 0/995 [00:00<?, ?it/s] Loading 0: 10%|▉ | 99/995 [00:01<00:13, 66.34it/s] Loading 0: 19%|█▉ | 193/995 [00:02<00:10, 79.45it/s] Loading 0: 25%|██▍ | 246/995 [00:03<00:10, 68.53it/s] Loading 0: 26%|██▌ | 257/995 [00:13<01:04, 11.42it/s] Loading 0: 30%|███ | 301/995 [00:14<00:46, 15.03it/s] Loading 0: 41%|████ | 407/995 [00:15<00:22, 25.99it/s] Loading 0: 51%|█████ | 508/995 [00:16<00:13, 35.29it/s] Loading 0: 53%|█████▎ | 529/995 [00:26<00:34, 13.34it/s] Loading 0: 62%|██████▏ | 614/995 [00:27<00:19, 19.22it/s] Loading 0: 72%|███████▏ | 715/995 [00:29<00:10, 27.12it/s] Loading 0: 81%|████████ | 801/995 [00:39<00:12, 15.75it/s] Loading 0: 84%|████████▍ | 838/995 [00:40<00:09, 17.41it/s] Loading 0: 93%|█████████▎| 922/995 [00:46<00:04, 16.27it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
maldv-spring-chicken-8x8b-v7-mkmlizer: quantized model in 57.552s
maldv-spring-chicken-8x8b-v7-mkmlizer: Processed model maldv/spring-chicken-8x8b in 140.613s
maldv-spring-chicken-8x8b-v7-mkmlizer: creating bucket guanaco-mkml-models
maldv-spring-chicken-8x8b-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
maldv-spring-chicken-8x8b-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/maldv-spring-chicken-8x8b-v7
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/maldv-spring-chicken-8x8b-v7/config.json
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/maldv-spring-chicken-8x8b-v7/special_tokens_map.json
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/maldv-spring-chicken-8x8b-v7/tokenizer_config.json
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/maldv-spring-chicken-8x8b-v7/flywheel_model.3.safetensors
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/maldv-spring-chicken-8x8b-v7/flywheel_model.0.safetensors
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/maldv-spring-chicken-8x8b-v7/flywheel_model.2.safetensors
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/maldv-spring-chicken-8x8b-v7/flywheel_model.1.safetensors
maldv-spring-chicken-8x8b-v7-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
maldv-spring-chicken-8x8b-v7-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.
maldv-spring-chicken-8x8b-v7-mkmlizer: warnings.warn(
maldv-spring-chicken-8x8b-v7-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.
maldv-spring-chicken-8x8b-v7-mkmlizer: warnings.warn(
maldv-spring-chicken-8x8b-v7-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()
maldv-spring-chicken-8x8b-v7-mkmlizer: return self.fget.__get__(instance, owner)()
maldv-spring-chicken-8x8b-v7-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
maldv-spring-chicken-8x8b-v7-mkmlizer: Saving duration: 0.239s
maldv-spring-chicken-8x8b-v7-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 10.379s
maldv-spring-chicken-8x8b-v7-mkmlizer: creating bucket guanaco-reward-models
maldv-spring-chicken-8x8b-v7-mkmlizer: Bucket 's3://guanaco-reward-models/' created
maldv-spring-chicken-8x8b-v7-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/maldv-spring-chicken-8x8b-v7_reward
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/maldv-spring-chicken-8x8b-v7_reward/config.json
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/maldv-spring-chicken-8x8b-v7_reward/special_tokens_map.json
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/maldv-spring-chicken-8x8b-v7_reward/tokenizer_config.json
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/maldv-spring-chicken-8x8b-v7_reward/merges.txt
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/maldv-spring-chicken-8x8b-v7_reward/vocab.json
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/maldv-spring-chicken-8x8b-v7_reward/tokenizer.json
maldv-spring-chicken-8x8b-v7-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/maldv-spring-chicken-8x8b-v7_reward/reward.tensors
Job maldv-spring-chicken-8x8b-v7-mkmlizer completed after 291.05s with status: succeeded
Stopping job with name maldv-spring-chicken-8x8b-v7-mkmlizer
Pipeline stage MKMLizer completed in 296.48s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service maldv-spring-chicken-8x8b-v7
Waiting for inference service maldv-spring-chicken-8x8b-v7 to be ready
Inference service maldv-spring-chicken-8x8b-v7 ready after 60.493364334106445s
Pipeline stage ISVCDeployer completed in 68.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.7008423805236816s
Received healthy response to inference request in 2.3110620975494385s
Received healthy response to inference request in 2.26274037361145s
Received healthy response to inference request in 2.4014477729797363s
Received healthy response to inference request in 2.3713276386260986s
5 requests
0 failed requests
5th percentile: 2.2724047183990477
10th percentile: 2.2820690631866456
20th percentile: 2.301397752761841
30th percentile: 2.3231152057647706
40th percentile: 2.3472214221954344
50th percentile: 2.3713276386260986
60th percentile: 2.3833756923675535
70th percentile: 2.395423746109009
80th percentile: 2.6613266944885257
90th percentile: 3.181084537506104
95th percentile: 3.4409634590148923
99th percentile: 3.6488665962219238
mean time: 2.609484052658081
Pipeline stage StressChecker completed in 13.68s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
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
maldv-spring-chicken-8x8b_v7 status is now deployed due to DeploymentManager action
maldv-spring-chicken-8x8b_v7 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics