submission_id: hastagaras-lp-8b-dpotest_v3

developer_uid: Hastagaras

status: inactive

model_repo: Hastagaras/LP-8B-DPOTEST

reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2

generation_params: {'temperature': 0.85, 'top_p': 1.0, 'min_p': 0.0, '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\nYou are {bot_name}. Write {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations must be enclosed in asterisks (*). The responses must be long and in third perspective of the story teller.\n\nDescription: {memory}\n", 'prompt_template': 'Example conversation:\n{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", 'prompt_template': '{prompt}\n', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}

timestamp: 2024-04-29T09:31:44+00:00

model_name: hastagaras-lp-8b-dpotest_v1

model_eval_status: success

double_thumbs_up: 48

thumbs_up: 101

thumbs_down: 29

num_battles: 5556

num_wins: 2936

celo_rating: 1176.31

entertaining: 7.0

stay_in_character: 8.35

user_preference: 7.1

safety_score: None

submission_type: basic

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: hastagaras-lp-8b-dpotest_v1

double_thumbs_up_ratio: 0.2696629213483146

feedback_count: 178

ineligible_reason: None

language_model: Hastagaras/LP-8B-DPOTEST

model_score: 7.483333333333333

model_size: 8B

reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2

single_thumbs_up_ratio: 0.5674157303370787

thumbs_down_ratio: 0.16292134831460675

thumbs_up_ratio: 0.8370786516853933

us_pacific_date: 2024-04-29

win_ratio: 0.5284377249820015