arxiv:2305.18365
KehanGuo
kguo2
·
AI & ML interests
large language model, molecule representation learning
Organizations
models 10
kguo2/Qwen2.5-3B-PRM-GRPO-SingleGPU
Updated
kguo2/finetune_demo
Text Generation • 8B • Updated • 5
kguo2/Qwen2.5-7B
8B • Updated • 2
kguo2/Qwen2.5-3B
3B • Updated • 2
kguo2/output_dir
Text Generation • 0.6B • Updated • 7
kguo2/Qwen2.5-3B-GRPO-test
Text Generation • 3B • Updated • 3
kguo2/Qwen2-0.5B-Instruct
Updated
kguo2/Qwen2.5-7B-GRPO-test
Updated
kguo2/Qwen2-0.5B-GRPO-test
0.5B • Updated • 3
kguo2/llama-2-uspto
Updated
datasets 11
kguo2/pubchem-100m-aug-80-20
Viewer • Updated • 134M • 605
kguo2/pubchem-20m-mixed-80-20
Viewer • Updated • 26.7M • 6
kguo2/pubchem-10m-mixed-80-20
Viewer • Updated • 12M • 191
kguo2/pubchem-30m-mixed-80-20
Viewer • Updated • 22.3M • 156
kguo2/pubchem-100m-mixed-80-20
Viewer • Updated • 111M • 10
kguo2/prm_data
Viewer • Updated • 2.29k • 4
kguo2/ift-scaffold-dataset
Viewer • Updated • 28.5k • 9
kguo2/scaffold_finetune
Viewer • Updated • 29k • 7
kguo2/smiles-dataset
Viewer • Updated • 29.3k • 11
kguo2/Qwen2-0.5B-GRPO-test
Viewer • Updated • 29.2k • 7