embedl/Cosmos-Reason2-2B-W4A16-Edge2-FlashHead
Image-Text-to-Text • 2B • Updated • 459 • 7
FlashHead
Efficient Drop-In Replacement for the Classification Head in Language Model Inference. https://github.com/embedl/flash-head
-
-
embedl/Qwen3-1.7B-FlashHead-W4A16
2B • Updated • 95 • 3 -
embedl/gemma-3-270m-it-FlashHead
0.3B • Updated • 44 • 3 -
embedl/Qwen3-0.6B-FlashHead
0.6B • Updated • 48 • 4 -
embedl/Qwen3-1.7B-FlashHead
2B • Updated • 47 • 3 -
embedl/Llama-3.2-1B-Instruct-FlashHead
1B • Updated • 47 • 4 -
embedl/Llama-3.2-3B-Instruct-FlashHead
3B • Updated • 64 • 4 -
embedl/Llama-3.2-3B-Instruct-FlashHead-W4A16
4B • Updated • 79 • 4 -
embedl/Llama-3.2-1B-Instruct-FlashHead-W4A16
2B • Updated • 69 • 6 -
embedl/gemma-3-1b-it-FlashHead
1.0B • Updated • 65 • 3 -
embedl/gemma-3-1b-it-FlashHead-W4A16
1B • Updated • 89 • 3