Mehar Bhatia
MeharBhatia
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 19 hours ago
Value Drifts: Tracing Value Alignment During LLM Post-Training
updated
a dataset
1 day ago
McGill-NLP/value-drifts
commented on
a paper
1 day ago
Value Drifts: Tracing Value Alignment During LLM Post-Training
Organizations
models
38
MeharBhatia/llama3_8b_ppo_sft_wildchat_chosen_oppose
266k
•
Updated
•
12
MeharBhatia/llama3_8b_ppo_sft_wildchat_chosen_support
266k
•
Updated
•
10
MeharBhatia/llama3_8b_ppo_sft_alpaca_chosen_oppose
266k
•
Updated
•
12
MeharBhatia/llama3_8b_ppo_sft_alpaca_chosen_support
266k
•
Updated
•
11
MeharBhatia/llama3_8b_simpo_sft_alpaca_chosen_oppose
266k
•
Updated
•
13
MeharBhatia/llama3_8b_simpo_sft_alpaca_chosen_support
266k
•
Updated
•
9
MeharBhatia/llama3_8b_simpo_sft_wildchat_chosen_support
266k
•
Updated
•
12
MeharBhatia/llama3_8b_simpo_sft_wildchat_chosen_oppose
266k
•
Updated
•
9
MeharBhatia/llama3_8b_dpo_sft_wildchat_chosen_oppose
266k
•
Updated
•
8
MeharBhatia/llama3_8b_dpo_sft_wildchat_chosen_support
266k
•
Updated
•
10