Parameters / Experts - How to run this model ;
#16 opened about 1 year ago
by 
DavidAU
DeepSeek R1 0528?
#15 opened about 1 year ago
by 
Thireus
This model almost completely loses Chinese ablities
👍 1
3
#14 opened about 1 year ago
by 
CHNtentes
Base version?
➕ 3
2
#13 opened about 1 year ago
by 
ToastyPigeon
Russian language is missing
1
#12 opened about 1 year ago
by 
Kosh69
Please, share the custom vLLM source you made
👀 1
#11 opened about 1 year ago
by 
hyunw55
Update metadata 🤗
#10 opened about 1 year ago
by 
merve
Model seems to not be performing correctly
1
#9 opened about 1 year ago
by 
daniel-ltw
Larger model?
🧠 2
#8 opened about 1 year ago
by 
blobbybob
number of experts +
🔥🧠 2
#7 opened about 1 year ago
by 
Danioken
Brainstorming
🧠 5
5
#6 opened about 1 year ago
by 
Downtown-Case
Further training/distillation needed?
👀 1
1
#5 opened about 1 year ago
by 
mingyi456
Besides pruning..
6
#4 opened about 1 year ago
by 
Lockout
Context size? YaRN still supported?
2
#3 opened about 1 year ago
by Thireus
Variants
#2 opened about 1 year ago
by 
someone13574
code
➕ 18
#1 opened about 1 year ago
by 
mrfakename