moyanwang
bigmoyan
AI & ML interests
AIGC / LLM / Large Multimodal Model/ Infra
Recent Activity
upvoted
a
paper
about 3 hours ago
Kimi-VL Technical Report
new activity
15 days ago
qyang1021/AIR-Bench-Dataset:损坏文件
new activity
16 days ago
qyang1021/AIR-Bench-Dataset:兄弟你是不是把历史文件都交到git里了……
Organizations
bigmoyan's activity
兄弟你是不是把历史文件都交到git里了……
#2 opened about 1 month ago
by
bigmoyan

同Instruct版本,不需要这个assert
#2 opened 17 days ago
by
bigmoyan

Remove channel num check
#1 opened 17 days ago
by
bigmoyan

Upload modeling_chatglm.py
#2 opened 20 days ago
by
bigmoyan

Fail to import vector_quantize and deepspeed
1
#1 opened about 1 month ago
by
bigmoyan

导入自己训练的模型时候报错:RuntimeError: Wrong Size for bin file load
4
#43 opened almost 2 years ago
by
vining
求助!报错OSError: [WinError 193] %1 不是有效的 Win32 应用程序。
2
#45 opened almost 2 years ago
by
ushow
Model load error
3
#2 opened almost 2 years ago
by
gaoxiao
docker image not available
1
#26 opened almost 2 years ago
by
lizhou3
请问这个加速版本还支持原版模型的quantize接口吗,4bit和8bit量化
3
#11 opened almost 2 years ago
by
goldenteethCN
ImportError: libcudart.so.12: cnnot open shared object file: No such file or directory
10
#13 opened almost 2 years ago
by
zangao
About the relationship between glm6b-bs8.ftm and original chatglm6b weights
3
#14 opened almost 2 years ago
by
thincal
About the 3090/4090/A10 device support
6
#15 opened almost 2 years ago
by
thincal
Why not support Windows?
1
#12 opened almost 2 years ago
by
Pevernow

Speed comparison with fastertransformer for ChatGLM?
2
#10 opened almost 2 years ago
by
xiangli
OSError: /lyraChatGLM/lyraChatGLM/libnvinfer_plugin.so: invalid ELF header
17
#8 opened almost 2 years ago
by
Laity0806
how to generating glm.cpython-38-x86_64-linux-gnu.so
8
#2 opened almost 2 years ago
by
SHAYINDAODSD
about 310 tokens/s
6
#6 opened almost 2 years ago
by
lchustc
TensorRT version Error
4
#7 opened almost 2 years ago
by
rayleee