Hsu Shihyueh's picture

9 2 6

Hsu Shihyueh

AIR-hl

·

AIR-hl

AI & ML interests

Nothing

Recent Activity

new activity 25 days ago

deepseek-ai/DeepSeek-V3.2:miss chat template file?

new activity 25 days ago

deepseek-ai/DeepSeek-V3.2:Humble request for a stable vLLM/SGLang deployment setup for DeepSeek-V3.2

new activity 5 months ago

miromind-ai/MiroVerse-v0.1:Where is the data file?

View all activity

Organizations

None yet

AIR-hl 's models 10

AIR-hl/Qwen2.5-1.5B-LD-DPO

AIR-hl/Mistral-7B-Base-WPO-bf16

Text Generation • 7B • Updated Jan 12 • 8

AIR-hl/Llama-3.2-3B-WPO

Text Generation • 4B • Updated Jan 7 • 9

AIR-hl/Llama-3.2-3B-DPO

Text Generation • 4B • Updated Jan 5 • 8 • 2

AIR-hl/Qwen2.5-1.5B-SimPO

Text Generation • 2B • Updated Jan 3 • 9

AIR-hl/Qwen2.5-1.5B-WPO

Text Generation • 2B • Updated Jan 3 • 9

AIR-hl/Qwen2.5-1.5B-DPO

Text Generation • 2B • Updated Jan 2 • 27

AIR-hl/Llama-3.2-1B-DPO

Text Generation • 1B • Updated Dec 24, 2024 • 20 •

AIR-hl/Llama-3.2-1B-ultrachat200k

Text Generation • 1B • Updated Nov 21, 2024 • 16 •

AIR-hl/Qwen2.5-1.5B-ultrachat200k

Text Generation • 2B • Updated Nov 20, 2024 • 19