Ryu Sangwon
ryusangwon
AI & ML interests
Text Generation, Writing Assistant, Summarization
Recent Activity
updated
a model
about 2 months ago
ryusangwon/dpo_beta0.7_general_nllb-200-distilled-1.3B
published
a model
about 2 months ago
ryusangwon/dpo_beta0.7_general_nllb-200-distilled-1.3B
updated
a model
about 2 months ago
ryusangwon/dpo_beta0.5_general_nllb-200-distilled-1.3B
Organizations
None yet
ryusangwon's activity
Is that few-shot learning updates the gradient?
1
#79 opened almost 2 years ago
by
ryusangwon
how to deal with KeyError: 'llama'?
#3 opened almost 2 years ago
by
ryusangwon
How to evaluate hellaswag with LLM?
1
#66 opened almost 2 years ago
by
ryusangwon