Song Li
SongTonyLi
·
AI & ML interests
None yet
Organizations
SongTonyLi/Llama-3.2-3B-Instruct-CPT-D1_chosen-then-SFT-D2_chosen-pref-mix
Text Generation
•
Updated
•
127
SongTonyLi/Llama-3.2-3B-Instruct-CPT-D1_chosen-pref-mix
Text Generation
•
Updated
•
78
SongTonyLi/Llama-3.2-3B-Instruct-CPT-D_chosen-pref-mix
Text Generation
•
Updated
•
136
SongTonyLi/Llama-3.2-3B-Instruct-SFT-D1_chosen-then-D2_chosen-pref-mix
Text Generation
•
Updated
•
127
SongTonyLi/Llama-3.2-3B-Instruct-SFT-D1_chosen-pref-mix
Text Generation
•
Updated
•
80
SongTonyLi/Llama-3.2-1B-Instruct-CPT-D1_chosen-then-SFT-D2_chosen-pref-mix2
Text Generation
•
Updated
•
67
SongTonyLi/Llama-3.2-1B-Instruct-CPT-D1_chosen-pref-mix2
Text Generation
•
Updated
•
58
SongTonyLi/Llama-3.2-1B-Instruct-CPT-D_chosen-pref-mix2
Text Generation
•
Updated
•
70
SongTonyLi/Llama-3.2-1B-Instruct-SFT-D1_chosen-then-D2_chosen-pref-mix2
Text Generation
•
Updated
•
69
SongTonyLi/Llama-3.2-1B-Instruct-SFT-D1_chosen-pref-mix2
Text Generation
•
Updated
•
52
SongTonyLi/llama_1B_dolly_15k_data
Viewer
•
Updated
•
15k
•
30
SongTonyLi/llama_1B_stem_data
Viewer
•
Updated
•
151k
•
37
Viewer
•
Updated
•
178k
•
30
SongTonyLi/tachibana_coding_10k
Viewer
•
Updated
•
104k
•
30
SongTonyLi/Magpie-Pro-Ultra-40K
Viewer
•
Updated
•
41.4k
•
33
SongTonyLi/Magpie-Pro-hard-8K
Viewer
•
Updated
•
8k
•
32
SongTonyLi/llama-1b-preference-merge-mix
Viewer
•
Updated
•
142k
•
39
•
1
SongTonyLi/dpo-mix_skywork_infinity
Viewer
•
Updated
•
131k
•
34
•
1
SongTonyLi/dpo-mix-shuffled
Viewer
•
Updated
•
44.2k
•
34
SongTonyLi/merged_orca_skywork_capybara_infinity_midL2_preference
Viewer
•
Updated
•
88k
•
28