Wang Weimin
weiminw
AI & ML interests
None yet
Recent Activity
New activity
5 days ago
Qwen/Qwen2-VL-7B-Instruct:如果利用VL模型获取视觉层的Embedding
New activity
5 days ago
Alibaba-NLP/gte-multilingual-base:模型结构名字后面还会更新吗
New activity
5 days ago
Alibaba-NLP/gte-multilingual-base:sparse embedding norm?
Organizations
None yet
weiminw's activity
如果利用VL模型获取视觉层的Embedding
#52 opened 5 days ago
by
weiminw
模型结构名字后面还会更新吗
#19 opened 5 days ago
by
weiminw
sparse embedding norm?
#17 opened 5 days ago
by
weiminw
is there possible get the sparse embedding?
3
#23 opened 5 days ago
by
weiminw
是否可以提供safetensors的文件和相关文件.
#5 opened about 1 month ago
by
weiminw
会有4bit或者8bit量化版本吗?
1
#3 opened about 2 months ago
by
weiminw
是否能出个Llama3.1-70B-Chinese-Chat 4bit 量化版本?
#9 opened 3 months ago
by
weiminw
有可能出一个70B的AWQ或者GPTQ-INT4的量化版本吗?
3
#4 opened 4 months ago
by
weiminw
在提示词使用结构化输出,内容会少很多, 甚至会出现幻觉!
1
#14 opened 4 months ago
by
weiminw
CUDA out of memory (4090 24G)
2
#44 opened 5 months ago
by
weiminw
关于openai compatible api
1
#41 opened 5 months ago
by
weiminw
slide_window报错
#2 opened 6 months ago
by
weiminw
Idea for a truly uncensored LLaMa-3-8B
10
#3 opened 7 months ago
by
Joseph717171
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 28.00 MiB. GPU
1
#1 opened 6 months ago
by
weiminw
是否有AWQ版本呢?
#40 opened 6 months ago
by
weiminw
多语言和ocr支持
2
#5 opened 6 months ago
by
weiminw
缺少加载和基本使用文档
#2 opened 8 months ago
by
weiminw