Resources

View closed (0)

Parameters / Experts - How to run this model ;

#16 opened 5 months ago by

DavidAU

DeepSeek R1 0528?

#15 opened 6 months ago by

Thireus

This model almost completely loses Chinese ablities

👍 1

#14 opened 6 months ago by

CHNtentes

Base version?

➕ 3

#13 opened 6 months ago by

ToastyPigeon

Russian language is missing

#12 opened 7 months ago by

Kosh69

Please, share the custom vLLM source you made

👀 1

#11 opened 7 months ago by

hyunw55

Update metadata 🤗

#10 opened 7 months ago by

merve

Model seems to not be performing correctly

#9 opened 7 months ago by

daniel-ltw

Larger model?

🧠 2

#8 opened 7 months ago by

blobbybob

number of experts +

🔥 🧠 2

#7 opened 7 months ago by

Danioken

Brainstorming

🧠 5

#6 opened 7 months ago by

Downtown-Case

Further training/distillation needed?

👀 1

#5 opened 7 months ago by

mingyi456

Besides pruning..

#4 opened 7 months ago by

Lockout

Context size? YaRN still supported?

#3 opened 7 months ago by

Thireus

Variants

#2 opened 7 months ago by

someone13574

code

➕ 18

#1 opened 7 months ago by

mrfakename