Song Li's picture

2 2

Song Li

SongTonyLi

·

SongTonyLi

AI & ML interests

None yet

Recent Activity

upvoted an article 25 days ago

An Introduction to Deep Reinforcement Learning

updated a model about 1 month ago

SongTonyLi/codellama-grpo-clip-0.1-peft-lora-r32-c2x86

published a model about 1 month ago

SongTonyLi/codellama-grpo-clip-0.1-peft-lora-r32-c2x86

View all activity

Organizations

SongTonyLi 's models 156

SongTonyLi/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix6

Text Generation • 1B • Updated Oct 3, 2024 • 1 •

SongTonyLi/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix5

Text Generation • 1B • Updated Oct 3, 2024 • 1 •

SongTonyLi/Llama-3.2-1B-Instruct-SFT-D_chosen-pref-mix4

Text Generation • 1B • Updated Oct 3, 2024 • 1 •

SongTonyLi/Llama-3.2-1B-Instruct-SFT-D_chosen-capybarae

Text Generation • 1B • Updated Sep 30, 2024 • 1 •

SongTonyLi/Llama-3.2-1B-Instruct-CPT-D_chosen-Magpie

Text Generation • 1B • Updated Sep 29, 2024 • 2 •

SongTonyLi/Llama-3.2-1B-Instruct-SFT-D_chosen-Magpie

Text Generation • 1B • Updated Sep 29, 2024 • 2 •

SongTonyLi/Llama-3.2-1B-Instruct-SFT-D_chosen-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 1B • Updated Sep 29, 2024 • 2 •

SongTonyLi/Llama-3.2-1B-Instruct-SFT-D1_chosen-then-D2_chosen-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 1B • Updated Sep 29, 2024 • 2

SongTonyLi/Llama-3.2-1B-Instruct-SFT-D1_chosen-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 1B • Updated Sep 29, 2024 • 1 •

SongTonyLi/Phi-3.5-mini-instruct-CPT-D1_chosen-then-DPO-D2a-dpo-mix-shuffled5

Text Generation • 4B • Updated Sep 27, 2024 • 1

SongTonyLi/Phi-3.5-mini-instruct-DPO-D1-dpo-mix-shuffled5

Text Generation • 4B • Updated Sep 27, 2024 • 1

SongTonyLi/Phi-3.5-mini-instruct-CPT-D1_chosen-then-SFT-D2_chosen-dpo-mix-shuffled5

Text Generation • 4B • Updated Sep 27, 2024 • 2

SongTonyLi/OpenELM-3B-DPO-D1-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 3B • Updated Sep 26, 2024 • 1

SongTonyLi/Phi-3.5-mini-instruct-CPT-D1_chosen-dpo-mix-shuffled5

Text Generation • 4B • Updated Sep 26, 2024

SongTonyLi/OpenELM-3B-CPT-D1_chosen-then-DPO-D2a-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 3B • Updated Sep 26, 2024 • 1

SongTonyLi/OpenELM-3B-SFT-D1_chosen-then-DPO_D2a-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 3B • Updated Sep 26, 2024 • 3

SongTonyLi/OpenELM-3B-CPT-D1_chosen-then-SFT-D2_chosen-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 3B • Updated Sep 25, 2024 • 4

SongTonyLi/OpenELM-3B-CPT-D1_chosen-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 3B • Updated Sep 25, 2024 • 1

SongTonyLi/OpenELM-3B-LoRA-128

Text Generation • 3B • Updated Sep 25, 2024 • 1

SongTonyLi/OpenELM-3B-LoRA-32

Text Generation • 3B • Updated Sep 25, 2024 • 1

SongTonyLi/OpenELM-1_1B-DPO-D1-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 1B • Updated Sep 25, 2024 • 1

SongTonyLi/OpenELM-1_1B-CPT-D1_chosen-then-DPO-D2a-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 1B • Updated Sep 25, 2024 • 2

SongTonyLi/OpenELM-450M-CPT-D1_chosen-then-SFT-D2_chosen-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 0.5B • Updated Sep 25, 2024 • 1

SongTonyLi/OpenELM-1_1B-CPT-D1_chosen-then-SFT-D2_chosen-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 1B • Updated Sep 25, 2024 • 1

SongTonyLi/OpenELM-1_1B-CPT-D1_chosen-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 1B • Updated Sep 25, 2024

SongTonyLi/OpenELM-1_1B-LoRA-128

Text Generation • 1B • Updated Sep 25, 2024 • 1

SongTonyLi/OpenELM-1_1B-LoRA-32

Text Generation • 1B • Updated Sep 25, 2024 • 1

SongTonyLi/OpenELM-270M-DPO-D1-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 0.3B • Updated Sep 25, 2024 • 1

SongTonyLi/OpenELM-270M-CPT-D1_chosen-then-DPO-D2a-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 0.3B • Updated Sep 25, 2024 • 1

SongTonyLi/OpenELM-450M-DPO-D1-HuggingFaceH4-ultrafeedback_binarized-Xlarge

Text Generation • 0.5B • Updated Sep 25, 2024 • 1