Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
szxllm
/
MultiModal
like
0
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
szxllm
commited on
Jan 17
Commit
bc2cf94
·
verified
·
1 Parent(s):
cd66851
Update README.md
Browse files
Files changed (1)
hide
show
README.md
+5
-3
README.md
CHANGED
Viewed
@@ -1,3 +1,5 @@
1
-
---
2
-
license: apache-2.0
3
-
---
1
+
---
2
+
license: apache-2.0
3
+
---
4
+
目前是基于一个GPU训练的版本,架构采用Yarn,GQA,MOE(可选),
5
+
预训练和后训练(SFT和GRPO)的数据包含文本,代码,图像。目前是没有图像训练过程。