100 4 37

Qingyun Li

qingy2024

qingy1337

AI & ML interests

None yet

Recent Activity

upvoted a collection about 21 hours ago

Qwen2.5-VL

new activity 2 days ago

HuggingFaceTB/smoltalk:Upload IMG_2267.jpeg

liked a model 4 days ago

DevQuasar/qingy2024.Qwarkstar-4B-Instruct-GGUF

View all activity

Organizations

None yet

qingy2024's activity

upvoted a collection about 21 hours ago

Qwen2.5-VL

Collection

Vision-language model series based on Qwen2.5 • 3 items • Updated about 11 hours ago • 136

New activity in HuggingFaceTB/smoltalk 2 days ago

Upload IMG_2267.jpeg

#5 opened about 2 months ago by

YungAge

liked 2 models 4 days ago

DevQuasar/qingy2024.Qwarkstar-4B-Instruct-GGUF

Text Generation • Updated 16 days ago • 186 • 1

bytedance-research/UI-TARS-7B-SFT

Image-Text-to-Text • Updated 2 days ago • 1.73k • 116

reacted to sometimesanotion's post with 🔥👍 4 days ago

Post

2508

I've managed a #1 score of 41.22% average for 14B parameter models on the Open LLM Leaderboard. As of this writing, sometimesanotion/Lamarck-14B-v0.7 is #8 for all models up to 70B parameters.

It took a custom toolchain around Arcee AI's mergekit to manage the complex merges, gradients, and LoRAs required to make this happen. I really like seeing features of many quality finetunes in one solid generalist model.