cehao's picture

4 1 3

cehao

cehao

·

AI & ML interests

None yet

Recent Activity

updated a collection 5 days ago

upvoted a paper 7 days ago

Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning

updated a model 7 days ago

cehao/Select2Reason-Qwen-7B

View all activity

Organizations

None yet

cehao's activity

updated a collection 5 days ago

Select2Reason

2 items • Updated 5 days ago

upvoted a paper 7 days ago

Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning

Paper • 2505.17266 • Published 16 days ago • 1

updated a model 7 days ago

cehao/Select2Reason-Qwen-7B

Updated 7 days ago • 10

updated a collection 7 days ago

Select2Reason

2 items • Updated 5 days ago

updated a collection 9 days ago

Select2Reason

2 items • Updated 5 days ago

published a model 10 days ago

cehao/Select2Reason-Qwen-7B

Updated 7 days ago • 10

New activity in open-thoughts/OpenThoughts-114k 3 months ago

The meaning of "distillation" - Does it require logit outputs from the teacher model?

#6 opened 4 months ago by

liked a model 3 months ago

cehao/Meta-Llama-3.1-8B-Instruct-LongFaith-SFT

Updated Feb 21 • 4 • 2

updated a model 4 months ago

cehao/Meta-Llama-3.1-8B-Instruct-LongFaith-SFT

Updated Feb 21 • 4 • 2

updated a collection 4 months ago

LongFaith

LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data • 2 items • Updated Feb 21

published a model 4 months ago

cehao/Meta-Llama-3.1-8B-Instruct-LongFaith-SFT

Updated Feb 21 • 4 • 2

updated a model 4 months ago

cehao/Meta-Llama-3.1-8B-Instruct-LongFaith-PO

Updated Feb 21 • 4 • 2

liked a model 4 months ago

cehao/Meta-Llama-3.1-8B-Instruct-LongFaith-PO

Updated Feb 21 • 4 • 2

published a model 4 months ago

cehao/Meta-Llama-3.1-8B-Instruct-LongFaith-PO

Updated Feb 21 • 4 • 2

liked a model almost 2 years ago

meta-llama/Llama-2-7b

Text Generation • Updated Apr 17, 2024 • 4.34k