cehao

cehao's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in open-thoughts/OpenThoughts-114k 15 days ago

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

4

#6 opened about 2 months ago by

saleem2

liked a model 19 days ago

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

Updated 24 days ago • 23 • 2

updated a model 24 days ago

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

Updated 24 days ago • 23 • 2

updated a collection 24 days ago

LongFaith

Collection

LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data • 2 items • Updated 24 days ago

published a model 24 days ago

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

Updated 24 days ago • 23 • 2

updated a model 24 days ago

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

Updated 24 days ago • 30 • 2

liked a model 24 days ago

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

Updated 24 days ago • 30 • 2

published a model 26 days ago

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

Updated 24 days ago • 30 • 2

New activity in OrionStarAI/OrionStar-Yi-34B-Chat over 1 year ago

请问用于微调的对话语料会覆盖多轮对话场景吗

1

#4 opened over 1 year ago by

cehao

请问用于微调的15w语料考虑开源吗

2

#2 opened over 1 year ago by

cehao

New activity in IDEA-CCNL/Ziya-Reader-13B-v1.0 over 1 year ago

能否考虑增强模型主动标注引用来源的意识呢？

1

#8 opened over 1 year ago by

cehao

liked a model over 1 year ago

meta-llama/Llama-2-7b

Text Generation • Updated Apr 17, 2024 • 4.27k