muziyongshixin
muziyongshixin
AI & ML interests
None yet
Recent Activity
new activity
about 1 month ago
Qwen/Qwen3-235B-A22B:8张80G显存的8卡A100能部署不?
new activity
4 months ago
cognitivecomputations/DeepSeek-R1-AWQ:MLA is not supported with moe_wna16 quantization. Disabling MLA.
new activity
4 months ago
cognitivecomputations/DeepSeek-R1-AWQ:Deployment framework
Organizations
None yet
muziyongshixin's activity
8张80G显存的8卡A100能部署不?
10
#9 opened about 1 month ago
by
Yuxin362
MLA is not supported with moe_wna16 quantization. Disabling MLA.
5
#7 opened 4 months ago
by
AMOSE
Deployment framework
27
#2 opened 5 months ago
by
xro7
why does the im_start and im_end token id exceed the tokenizer.voc_size?
1
#36 opened about 1 year ago
by
muziyongshixin
How does MergeKit's Moe Integration work?
6
#8 opened over 1 year ago
by
arhanovich
How does MergeKit's Moe Integration work?
6
#8 opened over 1 year ago
by
arhanovich
How does MergeKit's Moe Integration work?
6
#8 opened over 1 year ago
by
arhanovich