cycy233-misllm-v6-9-7-5

submission_id: cycy233-misllm-v6-9-7-5_v2

developer_uid: shiroe40

status: inactive

model_repo: cycy233/misllm_v6.9.7.5

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

generation_params: {'temperature': 1.0, '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': 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: 2024-06-14T06:52:43+00:00

model_name: base_f

model_eval_status: success

model_group: cycy233/misllm_v6.9.7.5

num_battles: 17588

num_wins: 9116

celo_rating: 1191.1

propriety_score: 0.6796996374935267

propriety_total_count: 7724.0

submission_type: basic

model_architecture: MistralForCausalLM

model_num_parameters: 7241732096.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: base_f

ineligible_reason: None

language_model: cycy233/misllm_v6.9.7.5

model_size: 7B

reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2

us_pacific_date: 2024-06-13

win_ratio: 0.5183079372299295

Resubmit model

Reference Models

Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-9-7-5-v2-mkmlizer
Waiting for job on cycy233-misllm-v6-9-7-5-v2-mkmlizer to finish
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║       /___/                                                         ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-9-7-5-v2-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.
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Downloaded to shared memory in 76.631s
cycy233-misllm-v6-9-7-5-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-9-7-5-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:02, 81.58it/s]
Loading 0:  70%|███████   | 204/291 [00:02<00:00, 91.58it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 79.37it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-9-7-5-v2-mkmlizer: quantized model in 15.434s
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Processed model cycy233/misllm_v6.9.7.5 in 94.349s
cycy233-misllm-v6-9-7-5-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-9-7-5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/config.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/special_tokens_map.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/tokenizer.model
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/tokenizer_config.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/tokenizer.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/flywheel_model.0.safetensors
cycy233-misllm-v6-9-7-5-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-9-7-5-v2-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.
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   warnings.warn(
cycy233-misllm-v6-9-7-5-v2-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.
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   warnings.warn(
cycy233-misllm-v6-9-7-5-v2-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.
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   warnings.warn(
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v33: ('http://mistralai-mixtral-8x7b-3473-v33-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42700->127.0.0.1:8080: read: connection reset by peer\n')
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Traceback (most recent call last):
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 509, in http_get
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     hf_transfer.download(
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Exception: Error while downloading: reqwest::Error { kind: Request, url: Url { scheme: "https", cannot_be_a_base: false, username: "", password: None, host: Some(Domain("cdn-lfs-us-1.huggingface.co")), port: None, path: "/repos/dc/b4/49cb0beb9d88e612ee4c9/f485ab2daabd6cfb584d1f5dbe44415c4037052562040fbb665d9d465a3487f2", query: Some("response-content-disposition=inline%3B+filename*%3DUTF-8%27%27pytorch_model.bin%3B+filename%3D%22pytorch_model.bin%22%3B&response-content-type=application%2Foctet-stream&Expires=1718607273&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxODYwNzI3M319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zL2RjL2I0L2RjYjQ0YWZmYTFmYTZkOWY2YWZlMGNhZjg2ZDM4ODJlMzljNGMzZTZiOWE0OWNiMGJlYjlkODhlNjEyZWU0YzkvZjQ4NWFiMmRhYWJkNmNmYjU4NGQxZjVkYmU0NDQxNWM0MDM3MDUyNTYyMDQwZmJiNjY1ZDlkNDY1YTM0ODdmMj9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=Wl9gGcLDT5muCMIBZGHFwpBrW6Xzf-jejSAABlPzPT%7E0Q-peJfFA0oSa%7ED5qw88EWNAGMZM5WrFhtm-llJM7NR4UhPiA0mqqrGMMlVSKDnxRYFt3ynd4EqhM1Y2gvKnvpoKnrGGarWEUCgQeiByH2pxiTvSVqwTav9X2FT0pUSPpGoDja6Xc-yLEv7qdKLZ3-%7EaQiWFaebQh-L0dP1bZ1%7EiEuEYeUrnagsFUT%7ERP50Dk6r1pwOvR6P3qr0IKQhJShYMrNonKzSO6A2zXUlEbMy0dSAA5Ht5r13kU2b8JZS1rdmIxtIcfMlSGYwDefum-J-T8k6x2T66etzbthqDwCA__&Key-Pair-Id=K2FPYV99P2N66Q"), fragment: None }, source: hyper::Error(Connect, ConnectError("dns error", Custom { kind: Uncategorized, error: "failed to lookup address information: Temporary failure in name resolution" })) }
cycy233-misllm-v6-9-7-5-v2-mkmlizer: The above exception was the direct cause of the following exception:
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Traceback (most recent call last):
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3335, in from_pretrained
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     resolved_archive_file = cached_file(
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/utils/hub.py", line 398, in cached_file
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     resolved_file = hf_hub_download(
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 119, in _inner_fn
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     return fn(*args, **kwargs)
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1492, in hf_hub_download
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     http_get(
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 520, in http_get
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     raise RuntimeError(
cycy233-misllm-v6-9-7-5-v2-mkmlizer: RuntimeError: An error occurred while downloading using `hf_transfer`. Consider disabling HF_HUB_ENABLE_HF_TRANSFER for better error handling.
cycy233-misllm-v6-9-7-5-v2-mkmlizer: The above exception was the direct cause of the following exception:
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Traceback (most recent call last):
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/code/uploading/reward.py", line 66, in <module>
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     cli()
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1128, in __call__
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     return self.main(*args, **kwargs)
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1053, in main
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     rv = self.invoke(ctx)
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1659, in invoke
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     return _process_result(sub_ctx.command.invoke(sub_ctx))
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1395, in invoke
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     return ctx.invoke(self.callback, **ctx.params)
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 754, in invoke
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     return __callback(*args, **kwargs)
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/code/uploading/reward.py", line 29, in tensorize_reward_model
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     model, config, tokenizer = download_from_huggingface(repo_id, revision, hf_auth_token)
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/code/uploading/reward.py", line 44, in download_from_huggingface
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     model = AutoModelForSequenceClassification.from_pretrained(
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 563, in from_pretrained
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     return model_class.from_pretrained(
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3417, in from_pretrained
cycy233-misllm-v6-9-7-5-v2-mkmlizer:     raise EnvironmentError(
cycy233-misllm-v6-9-7-5-v2-mkmlizer: OSError: Can't load the model for 'ChaiML/reward_gpt2_medium_preference_24m_e2'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'ChaiML/reward_gpt2_medium_preference_24m_e2' is the correct path to a directory containing a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.
Job cycy233-misllm-v6-9-7-5-v2-mkmlizer completed after 134.68s with status: failed
Stopping job with name cycy233-misllm-v6-9-7-5-v2-mkmlizer
%s, retrying in %s seconds...
Starting job with name cycy233-misllm-v6-9-7-5-v2-mkmlizer
Waiting for job on cycy233-misllm-v6-9-7-5-v2-mkmlizer to finish
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║     _____            __           __                                ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║       /___/                                                         ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  belonging to:                                                      ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-9-7-5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-9-7-5-v2-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.
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Downloaded to shared memory in 171.201s
cycy233-misllm-v6-9-7-5-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-9-7-5-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:00, 297.21it/s]
Loading 0:  34%|███▎      | 98/291 [00:01<00:03, 55.17it/s] 
Loading 0:  70%|███████   | 204/291 [00:02<00:01, 77.22it/s]
Loading 0: 100%|██████████| 291/291 [00:03<00:00, 72.07it/s]
                                                            
You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
cycy233-misllm-v6-9-7-5-v2-mkmlizer: quantized model in 15.494s
cycy233-misllm-v6-9-7-5-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-9-7-5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/config.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/tokenizer.model
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/tokenizer_config.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/special_tokens_map.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/tokenizer.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-misllm-v6-9-7-5-v2/flywheel_model.0.safetensors
cycy233-misllm-v6-9-7-5-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-misllm-v6-9-7-5-v2-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.
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   warnings.warn(
cycy233-misllm-v6-9-7-5-v2-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.
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   warnings.warn(
cycy233-misllm-v6-9-7-5-v2-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()
cycy233-misllm-v6-9-7-5-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Saving duration: 0.412s
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 12.367s
cycy233-misllm-v6-9-7-5-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-misllm-v6-9-7-5-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-misllm-v6-9-7-5-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-misllm-v6-9-7-5-v2_reward
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-7-5-v2_reward/tokenizer_config.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-misllm-v6-9-7-5-v2_reward/special_tokens_map.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-misllm-v6-9-7-5-v2_reward/config.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-misllm-v6-9-7-5-v2_reward/merges.txt
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-misllm-v6-9-7-5-v2_reward/vocab.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-misllm-v6-9-7-5-v2_reward/tokenizer.json
cycy233-misllm-v6-9-7-5-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-misllm-v6-9-7-5-v2_reward/reward.tensors
Job cycy233-misllm-v6-9-7-5-v2-mkmlizer completed after 236.39s with status: succeeded
Stopping job with name cycy233-misllm-v6-9-7-5-v2-mkmlizer
Pipeline stage MKMLizer completed in 374.18s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-misllm-v6-9-7-5-v2
Waiting for inference service cycy233-misllm-v6-9-7-5-v2 to be ready
Inference service cycy233-misllm-v6-9-7-5-v2 ready after 30.153634071350098s
Pipeline stage ISVCDeployer completed in 37.12s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9923624992370605s
Received healthy response to inference request in 1.1679282188415527s
Received healthy response to inference request in 1.1821362972259521s
Received healthy response to inference request in 1.153946876525879s
Received healthy response to inference request in 1.192033290863037s
5 requests
0 failed requests
5th percentile: 1.1567431449890138
10th percentile: 1.1595394134521484
20th percentile: 1.1651319503784179
30th percentile: 1.1707698345184325
40th percentile: 1.1764530658721923
50th percentile: 1.1821362972259521
60th percentile: 1.1860950946807862
70th percentile: 1.19005389213562
80th percentile: 1.5520991325378422
90th percentile: 2.2722308158874513
95th percentile: 2.6322966575622555
99th percentile: 2.9203493309020994
mean time: 1.5376814365386964
Pipeline stage StressChecker completed in 8.59s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.05s
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
cycy233-misllm-v6-9-7-5_v2 status is now deployed due to DeploymentManager action
cycy233-misllm-v6-9-7-5_v2 status is now inactive due to auto deactivation removed underperforming models

Start Time:

End Time:

Step (in hours or minutes, e.g. 1h, 10m):

Usage Metrics

Latency Metrics

Model Developer	Ranking	Ranking By Group	Elo Rating	Elo Rating By Group	Alignment Score	Alignment Question Responses	Submission ID	Parameters	Huggingface Repository	Variant	Number of Battles	Number of Battles By Group	Win Ratio	Win Ratio By Group	Type	Reward Repo	Best of	Max Input Tokens	Max Output Tokens	Model Architecture	Model Group	Date	Elo Norm	Alignment Norm	Alt Ranking	Alt Ranking By Group	Elo Rank	Alignment Rank
Jellywibble	1	1	1264.70	1266.41	0.71	5803.0	jellywibble-lora-120k-pr_2827_v2	8B	Jellywibble/lora_120k_pref_data_ep2	nitral-ai-hathor-l3-8b-v-01_v1	30751	285696	0.60	0.60	basic	ChaiML/gpt2_xl_pairwise_89m_step_347634	16.0	512.0	64.0	LlamaForCausalLM	Jellywibble/lora_120k_pr	2024-07-04	1.81	0.30	17	17	3	295
kay5555	2	1	1266.41	1266.41	0.70	6896.0	jellywibble-lora-120k-pr_2827_v5	8B	Jellywibble/lora_120k_pref_data_ep2	nitral-ai-hathor-l3-8b-v-01_v1	40418	285696	0.59	0.60	basic	ChaiML/gpt2_xl_pairwise_89m_step_347634	16.0	512.0	64.0	LlamaForCausalLM	Jellywibble/lora_120k_pr	2024-07-04	1.85	-0.26	108	17	1	500
robert_irvine	3	3	1236.91	1238.59	0.73	5655.0	nitral-ai-hathor-l3-8b-v-01_v12	8B	Nitral-AI/Hathor-L3-8B-v.01	nitral-ai-hathor-l3-8b-v-01_v12	32705	1081988	0.56	0.58	basic	ChaiML/gpt2_xl_pairwise_89m_step_347634	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-07-05	1.18	0.91	1	1	10	126
robert_irvine	4	3	1237.64	1238.59	0.72	11740.0	nitral-ai-hathor-l3-8b-v-01_v42	8B	Nitral-AI/Hathor-L3-8B-v.01	nitral-ai-hathor-l3-8b-v-01_v42	69123	1081988	0.52	0.58	basic	Jellywibble/CHAI_alignment_reward_model	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-07-06	1.19	0.87	2	1	8	133
robert_irvine	5	3	1238.43	1238.59	0.72	11197.0	nitral-ai-hathor-l3-8b-v-01_v43	8B	Nitral-AI/Hathor-L3-8B-v.01	nitral-ai-hathor-l3-8b-v-01_v43	65015	1081988	0.51	0.58	basic	Jellywibble/CHAI_alignment_reward_model	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-07-06	1.21	0.83	3	1	7	146
Jellywibble	6	6	1265.97	1265.97	0.70	6130.0	jellywibble-quantumenigm_5980_v2	8B	Jellywibble/QuantumEnigma-cp1500	quantum-enigma-cp1500	35750	35750	0.61	0.61	basic	ChaiML/gpt2_xl_pairwise_89m_step_347634	16.0	512.0	64.0	LlamaForCausalLM	Jellywibble/QuantumEnigm	2024-07-06	1.84	-0.42	157	157	2	557
kay5555	7	1	1261.11	1266.41	0.70	7034.0	jellywibble-lora-120k-pr_2827_v3	8B	Jellywibble/lora_120k_pref_data_ep2	nitral-ai-hathor-l3-8b-v-01_v1	40661	285696	0.58	0.60	basic	ChaiML/gpt2_xl_pairwise_89m_step_347634	16.0	512.0	64.0	LlamaForCausalLM	Jellywibble/lora_120k_pr	2024-07-04	1.73	-0.32	122	17	4	521
robert_irvine	8	3	1237.31	1238.59	0.72	5471.0	nitral-ai-hathor-l3-8b-v-01_v11	8B	Nitral-AI/Hathor-L3-8B-v.01	nitral-ai-hathor-l3-8b-v-01_v11	32108	1081988	0.57	0.58	basic	ChaiML/gpt2_xl_pairwise_89m_step_347634	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-07-05	1.19	0.58	9	1	9	210
dzhao1	9	9	1234.33	1234.33	0.72	7455.0	chaiml-sao10k-l3-rp-v3-3_v2	8B	ChaiML/sao10k-l3-rp-v3-3	chaiml-sao10k-l3-rp-v3-3_v2	15854	414605	0.58	0.58	basic	ChaiML/gpt2_xl_pairwise_89m_step_347634	8.0	1024.0	64.0	LlamaForCausalLM	ChaiML/sao10k-l3-rp-v3-3	2024-07-02	1.12	0.57	10	4	12	215
robert_irvine	10	3	1235.93	1238.59	0.72	5365.0	nitral-ai-hathor-l3-8b-v-01_v38	8B	Nitral-AI/Hathor-L3-8B-v.01	nitral-ai-hathor-l3-8b-v-01_v38	31159	1081988	0.58	0.58	basic	Jellywibble/CHAI_alignment_reward_model	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-07-05	1.15	0.47	11	1	11	240
robert_irvine	11	3	1238.59	1238.59	0.71	5261.0	nitral-ai-hathor-l3-8b-v-01_v41	8B	Nitral-AI/Hathor-L3-8B-v.01	nitral-ai-hathor-l3-8b-v-01_v41	30522	1081988	0.58	0.58	basic	ChaiML/gpt2_xl_pairwise_89m_step_347634	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-07-05	1.21	0.34	14	1	6	283
kay5555	12	1	1260.05	1266.41	0.70	7065.0	jellywibble-lora-120k-pr_2827_v4	8B	Jellywibble/lora_120k_pref_data_ep2	nitral-ai-hathor-l3-8b-v-01_v1	40196	285696	0.58	0.60	basic	ChaiML/gpt2_xl_pairwise_89m_step_347634	16.0	512.0	64.0	LlamaForCausalLM	Jellywibble/lora_120k_pr	2024-07-04	1.71	-0.62	217	17	5	625
dzhao1	13	9	1220.66	1234.33	0.73	5650.0	chaiml-sao10k-l3-rp-v3-3_v1	8B	ChaiML/sao10k-l3-rp-v3-3	chaiml-sao10k-l3-rp-v3-3_v1	11815	414605	0.57	0.58	basic	ChaiML/gpt2_medium_pairwise_60m_step_937500	8.0	1024.0	64.0	LlamaForCausalLM	ChaiML/sao10k-l3-rp-v3-3	2024-07-02	0.80	0.97	4	4	50	110
nguyenzzz	14	14	1216.48	1219.12	0.73	5314.0	meseca-15062024-c1_v3	8B	meseca/15062024-c1	meseca-15062024-c1_v3	10944	33263	0.56	0.56	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	8.0	1024.0	64.0	LlamaForCausalLM	meseca/15062024-c1	2024-07-01	0.71	1.12	7	7	94	90
R136a1	15	15	1220.22	1220.22	0.73	9252.0	r136a1-slerp8bv2_v2	8B	R136a1/Slerp8Bv2	r136a1-slerp8bv2_v1	9830	33452	0.55	0.55	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	R136a1/Slerp8Bv2	2024-06-25	0.79	0.95	5	5	55	116
dzhao1	16	16	1227.27	1227.27	0.72	5044.0	sao10k-l3-rp-v3-3_v9	8B	Sao10K/L3-RP-v3.3	sao10k-l3-rp-v3-3_v9	10311	3817665	0.58	0.58	basic	ChaiML/gpt2_xl_pairwise_89m_step_347634	8.0	1024.0	64.0	LlamaForCausalLM	Sao10K/L3-RP-v3.3	2024-07-01	0.95	0.62	8	8	18	200
Nitral-AI	17	3	1217.37	1238.59	0.73	8490.0	nitral-ai-hathor-l3-8b-v-02_v12	8B	Nitral-AI/Hathor-L3-8B-v.02	nitral-ai-hathor-l3-8b-v02	17317	1081988	0.53	0.58	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-06-22	0.73	1.02	6	1	80	104
robert_irvine	18	3	1230.38	1238.59	0.71	5413.0	nitral-ai-hathor-l3-8b-v-01_v37	8B	Nitral-AI/Hathor-L3-8B-v.01	nitral-ai-hathor-l3-8b-v-01_v37	31623	1081988	0.57	0.58	basic	Jellywibble/CHAI_alignment_reward_model	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-07-05	1.03	0.39	13	1	16	271
c.gato	19	19	1198.10	1208.35	0.74	5964.0	cgato-thesalt-rp-l3-8b-d_7209_v3	8B	cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.8.2	cgato-thesalt-rp-l3-8b-d_7209_v3	22762	626274	0.51	0.55	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	cgato/TheSalt-RP-L3-8b-D	2024-07-04	0.29	1.73	46	46	349	35
nguyenzzz	20	20	1164.75	1164.75	0.77	8354.0	meseca-20062024-c1-dpo-1e_v2	8B	meseca/20062024-c1-dpo-1e	meseca-20062024-c1-dpo-1e_v2	14942	30221	0.48	0.48	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	meseca/20062024-c1-dpo-1	2024-06-27	-0.48	3.03	274	274	698	5
Jellywibble	21	21	1152.73	1152.73	0.78	5334.0	jellywibble-nguy-alignme_4960_v1	8B	Jellywibble/nguy-alignment-regression-cp128	meseca-20062024-c1_v1	31528	61623	0.46	0.46	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Jellywibble/nguy-alignme	2024-07-05	-0.75	3.49	303	303	729	2
PawanOsman	22	22	1226.26	1232.68	0.71	5567.0	pawankrd-cosmosrp_v35	8B	PawanKrd/CosmosRP	pawankrd-cosmosrp_v35	33039	1713349	0.56	0.75	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	PawanKrd/CosmosRP	2024-07-05	0.93	0.31	19	19	20	290
dzhao1	23	9	1208.39	1234.33	0.73	6597.0	chaiml-sao10k-l3-rp-v3-3_v3	8B	ChaiML/sao10k-l3-rp-v3-3	chaiml-sao10k-l3-rp-v3-3_v3	13662	414605	0.55	0.58	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	8.0	1024.0	64.0	LlamaForCausalLM	ChaiML/sao10k-l3-rp-v3-3	2024-07-03	0.52	1.06	15	4	200	96
PawanOsman	24	22	1205.88	1232.68	0.73	6425.0	pawankrd-cosmosrp_v36	8B	PawanKrd/CosmosRP	pawankrd-cosmosrp_v36	37297	1713349	0.52	0.75	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	PawanKrd/CosmosRP	2024-07-06	0.46	1.15	21	19	241	82
Jellywibble	25	25	1204.84	1204.84	0.73	7424.0	jellywibble-hathor-stabl_8901_v1	8B	Jellywibble/Hathor_Stable-v0.2-L3-8B	nitral-ai-hathor-l3-8b-v-01_v1	15675	43096	0.54	0.54	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Jellywibble/Hathor_Stabl	2024-07-03	0.44	1.16	25	25	252	81
Hastagaras	26	26	1215.54	1215.54	0.72	19901.0	hastagaras-ultimatej-8b-l3-br_v1	8B	Hastagaras/UltimateJ-8B-L3-BR	hastagaras-ultimatej-8b-l3-br_v1	15513	15513	0.57	0.57	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Hastagaras/UltimateJ-8B-	2024-06-25	0.69	0.70	12	12	103	179
c.gato	27	27	1204.93	1204.93	0.73	12623.0	cgato-thesalt-rp-l3-8b-v0-3-2_v9	8B	cgato/TheSalt-RP-L3-8b-v0.3.2	cgato-thesalt-rp-l3-8b-v0-3-2_v9	26206	119491	0.55	0.63	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	cgato/TheSalt-RP-L3-8b-v	2024-06-19	0.44	1.12	27	27	248	86
Jellywibble	28	28	1203.54	1203.82	0.73	6368.0	jellywibble-qlora-120k-p_350_v2	8B	Jellywibble/qlora_120k_pref_data_ep1	nitral-ai-hathor-l3-8b-v-01_v1	13568	26921	0.52	0.52	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Jellywibble/qlora_120k_p	2024-07-03	0.41	1.17	34	34	276	79
Azazelle	29	29	1219.06	1219.78	0.72	5461.0	azazelle-l3-hecate-8b-v1-0_v2	8B	Azazelle/L3-Hecate-8B-v1.0	azazelle-l3-hecate-8b-v1-0_v1	31599	136923	0.56	0.56	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Azazelle/L3-Hecate-8B-v1	2024-07-05	0.77	0.50	16	16	63	234
PawanOsman	30	22	1231.99	1232.68	0.71	5670.0	pawankrd-cosmosrp_v34	8B	PawanKrd/CosmosRP	pawankrd-cosmosrp_v34	32737	1713349	0.56	0.75	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	PawanKrd/CosmosRP	2024-07-05	1.06	-0.06	73	19	15	429
Jellywibble	31	21	1150.24	1152.73	0.77	5324.0	jellywibble-nguy-alignme_5302_v1	8B	Jellywibble/nguy-alignment-regression-ep3	meseca-20062024-c1_v1	30095	61623	0.46	0.46	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Jellywibble/nguy-alignme	2024-07-05	-0.81	3.42	312	303	732	4
nguyenzzz	32	32	1163.58	1163.58	0.76	7186.0	meseca-20062024-c1-dpo-2e_v2	8B	meseca/20062024-c1-dpo-2e	meseca-20062024-c1-dpo-2e_v2	13424	24698	0.48	0.48	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	meseca/20062024-c1-dpo-2	2024-06-27	-0.51	2.84	282	282	704	8
Nitral-AI	33	3	1210.44	1238.59	0.72	12150.0	nitral-ai-hathor-l3-8b-v-02_v14	8B	Nitral-AI/Hathor-L3-8B-v.02	nitral-ai-hathor-l3-8b-v02	25571	1081988	0.51	0.58	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-06-22	0.57	0.84	20	1	176	142
PawanOsman	34	22	1223.32	1232.68	0.71	14566.0	pawankrd-cosmosrp_v24	8B	PawanKrd/CosmosRP	pawankrd-cosmosrp_v24	30258	1713349	0.58	0.75	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	PawanKrd/CosmosRP	2024-06-21	0.86	0.28	28	19	34	306
Nitral-AI	35	3	1217.44	1238.59	0.72	8230.0	nitral-ai-hathor-l3-8b-v-02_v11	8B	Nitral-AI/Hathor-L3-8B-v.02	nitral-ai-hathor-l3-8b-v02	17654	1081988	0.53	0.58	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-06-22	0.73	0.52	18	1	79	226
Jellywibble	36	1	1233.52	1266.41	0.70	5966.0	jellywibble-lora-120k-pr_2827_v1	8B	Jellywibble/lora_120k_pref_data_ep2	nitral-ai-hathor-l3-8b-v-01_v1	12653	285696	0.56	0.60	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Jellywibble/lora_120k_pr	2024-07-03	1.10	-0.19	102	17	13	480
R136a1	37	37	1214.27	1214.27	0.72	11654.0	r136a1-slerp8bv1_v1	8B	R136a1/Slerp8Bv1	r136a1-slerp8bv1_v1	24124	24124	0.54	0.54	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	R136a1/Slerp8Bv1	2024-06-24	0.66	0.61	22	22	122	203
robert_irvine	38	38	1190.48	1199.63	0.74	6517.0	nousresearch-meta-llama_4941_v78	8B	NousResearch/Meta-Llama-3-8B-Instruct	nousresearch-meta-llama_4941_v78	13904	274135	0.53	0.53	basic	ChaiML/gpt2_medium_pairwise_60m_step_937500	16.0	512.0	64.0	LlamaForCausalLM	NousResearch/Meta-Llama-	2024-07-03	0.11	1.61	112	67	460	42
Nitral-AI	39	3	1216.49	1238.59	0.72	10531.0	nitral-ai-hathor-l3-8b-v-01_v9	8B	Nitral-AI/Hathor-L3-8B-v.01	nitral-ai-hathor-l3-8b-v01	21595	1081988	0.52	0.58	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor-L3-8B-v	2024-06-22	0.71	0.50	24	1	93	236
Nitral-AI	40	40	1214.50	1214.50	0.72	9792.0	nitral-ai-hathor-unstabl_1363_v2	8B	Nitral-AI/Hathor_Unstable-L3-8B-v0.3	nitral-ai-hathor-03_1363_v1	20473	70699	0.53	0.55	basic	ChaiML/reward_gpt2_medium_preference_24m_e2	16.0	512.0	64.0	LlamaForCausalLM	Nitral-AI/Hathor_Unstabl	2024-06-22	0.66	0.57	23	23	116	212