Chenhao Guan

Dsg2

·

Dsg2

AI & ML interests

"Built in a cave with a box of scraps" Training small language models on low end consumer hardware.

Recent Activity

published a model about 11 hours ago

Dsg2/LS-Micro-Base

liked a model about 12 hours ago

opencerebral/Boris-2-Preview-2

liked a model about 12 hours ago

Anjaneyalu/gpt2-124m-fineweb-edu

View all activity

Organizations

None yet

published a model about 11 hours ago

Dsg2/LS-Micro-Base

Updated about 11 hours ago

liked 2 models about 12 hours ago

opencerebral/Boris-2-Preview-2

Text Generation • 0.1B • Updated 1 day ago • 10 • 2

Anjaneyalu/gpt2-124m-fineweb-edu

Text Generation • 0.1B • Updated about 12 hours ago • 9 • 1

updated a collection about 12 hours ago

LSEXP

Experimental LaoShu models. • 1 item • Updated about 12 hours ago

updated a model 18 days ago

Dsg2/LS-Tiny-Base-GGUF

Text Generation • 20.3M • Updated 18 days ago • 131

published a model 18 days ago

Dsg2/LS-Tiny-Base-GGUF

Text Generation • 20.3M • Updated 18 days ago • 131

New activity in Dsg2/LS2.5-108M-A17M-Base-GGUF 19 days ago

Can you please release the non-gguf models and training code as well? That would be great

#1 opened 22 days ago by

updated a dataset 19 days ago

Dsg2/MiniCPM5-2B-distill

Viewer • Updated 19 days ago • 397k • 61

published a dataset 21 days ago

Dsg2/MiniCPM5-2B-distill

Viewer • Updated 19 days ago • 397k • 61

updated a collection 29 days ago

LS2.5

Built on LS2's foundation, LS2.5 introduces a 16k vocab tokenizer to improve efficiency. • 3 items • Updated 29 days ago

updated 2 models 29 days ago

Dsg2/LS2.5-108M-A17M-Coder-GGUF

Text Generation • 58.7M • Updated 29 days ago • 137 • 1

Dsg2/LS2.5-108M-A17M-Chat-GGUF

Text Generation • 58.7M • Updated 29 days ago • 126 • 1

updated a model 30 days ago

Dsg2/LS2.5-108M-A17M-Base-GGUF

Text Generation • 58.7M • Updated 29 days ago • 97

updated a collection about 1 month ago

LS2.5

Built on LS2's foundation, LS2.5 introduces a 16k vocab tokenizer to improve efficiency. • 3 items • Updated 29 days ago

published a model about 1 month ago

Dsg2/LS2.5-108M-A17M-Base-GGUF

Text Generation • 58.7M • Updated 29 days ago • 97

liked a model about 1 month ago

singam96/ShadeNet-3.2-5M

Image-to-Image • Updated Sep 20 • 30 • 3

liked a dataset about 1 month ago

openbmb/UltraData-Code

Viewer • Updated 6 days ago • 267M • 31.3k • 210

liked a model about 1 month ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Image-Text-to-Text • 177B • Updated 23 days ago • 6.44M • 978

updated a collection about 1 month ago

LS1.5

Experimental models: testing next gen algorithms • 2 items • Updated Sep 21