·
AI & ML interests
None yet
Organizations
MeharBhatia/llama3_3b_sft_hhrlhf
4B • Updated • 8
MeharBhatia/llama3_3b_sft_ultrafeedback
4B • Updated • 9
MeharBhatia/llama3_8b_ppo_sft_wildchat_chosen_oppose
266k • Updated • 9
MeharBhatia/llama3_8b_ppo_sft_wildchat_chosen_support
266k • Updated • 7
MeharBhatia/llama3_8b_ppo_sft_alpaca_chosen_oppose
266k • Updated • 7
MeharBhatia/llama3_8b_ppo_sft_alpaca_chosen_support
266k • Updated • 10
MeharBhatia/llama3_8b_simpo_sft_alpaca_chosen_oppose
266k • Updated • 10
MeharBhatia/llama3_8b_simpo_sft_alpaca_chosen_support
266k • Updated • 7
MeharBhatia/llama3_8b_simpo_sft_wildchat_chosen_support
266k • Updated • 9
MeharBhatia/llama3_8b_simpo_sft_wildchat_chosen_oppose
266k • Updated • 9
MeharBhatia/llama3_8b_dpo_sft_wildchat_chosen_oppose
266k • Updated • 7
MeharBhatia/llama3_8b_dpo_sft_wildchat_chosen_support
266k • Updated • 8
MeharBhatia/llama3_8b_dpo_sft_alpaca_chosen_oppose
266k • Updated • 10
MeharBhatia/llama3_8b_dpo_sft_alpaca_chosen_support
266k • Updated • 11
MeharBhatia/qwen3_8b_ppo_sft_wildchat_chosen_support
308k • Updated • 9
MeharBhatia/qwen3_8b_ppo_sft_alpaca_chosen_oppose
308k • Updated • 7
MeharBhatia/qwen3_8b_ppo_sft_alpaca_chosen_support
308k • Updated • 10
MeharBhatia/qwen3_8b_simpo_sft_wildchat_chosen_support
308k • Updated • 8
MeharBhatia/qwen3_8b_simpo_sft_alpaca_chosen_oppose
308k • Updated • 6
MeharBhatia/qwen3_8b_simpo_sft_alpaca_chosen_support
308k • Updated • 18
MeharBhatia/qwen3_8b_dpo_sft_wildchat_chosen_oppose
308k • Updated • 7
MeharBhatia/qwen3_8b_dpo_sft_wildchat_chosen_support
308k • Updated • 9
MeharBhatia/qwen3_8b_rm_sft_wildchat_chosen_support
8B • Updated • 5
MeharBhatia/qwen3_8b_rm_sft_wildchat_chosen_oppose
8B • Updated • 4
MeharBhatia/qwen3_8b_sft_wildchat
8B • Updated • 11
MeharBhatia/llama3_8b_rm_sft_wildchat_chosen_oppose
8B • Updated • 7
MeharBhatia/llama3_8b_rm_sft_alpaca_chosen_oppose
8B • Updated • 9
MeharBhatia/qwen3_8b_rm_sft_alpaca_chosen_oppose
8B • Updated • 13
MeharBhatia/llama3_8b_rm_sft_wildchat_chosen_support
8B • Updated • 7
MeharBhatia/llama3_8b_rm_sft_alpaca_chosen_support
8B • Updated • 6