SwiftFormer 论文介绍了一种新的高效加性注意力机制,该机制有效地用线性元素乘法取代了自注意力计算中的二次矩阵乘法运算。
Updated 2024-11-22 16:44:21 +08:00
1
Updated 2024-11-22 16:18:09 +08:00
CodeFuse-CodeGeeX2-6B
Updated 2024-11-22 16:02:22 +08:00
m3e-base
Updated 2024-11-22 13:55:41 +08:00
internlm2_5-7b-chat
Updated 2024-11-22 13:27:24 +08:00
Yi-1.5-9B-Chat
Updated 2024-11-22 12:50:24 +08:00
Qwen2-VL-2B-Instruct
Updated 2024-11-22 09:42:12 +08:00
Updated 2024-11-22 09:39:51 +08:00
OneKE
Updated 2024-11-21 21:59:23 +08:00
openchat_3.5
Updated 2024-11-21 19:15:36 +08:00
AquilaChat2-7B
Updated 2024-11-21 19:07:59 +08:00
PDF-Extract-Kit
Updated 2024-11-21 18:15:19 +08:00
aiXcoder-7b-base
Updated 2024-11-21 15:02:36 +08:00
BART文本纠错-中文-通用领域-large
Updated 2024-11-21 11:15:41 +08:00
Qwen2.5-14B-Instruct-GPTQ-Int4
Updated 2024-11-21 11:01:02 +08:00