Joushe
joushe
ยท
AI & ML interests
None yet
Organizations
None yet
mmproj-qwen3-omni-30B-F16-fixed.gguf is 32.5GB
#1 opened 2 months ago
by
joushe
Can I request a higher quantization, such as 3-bit or 2-bit awq?
1
#2 opened 5 months ago
by
win10
Can't load in ollama
4
#6 opened over 1 year ago
by
joushe
May I ask how did you make Lora realize multiple concepts, and do not express at all without entering a specific prompt?
5
#5 opened about 3 years ago
by
joushe
The model you made is great, can you show me the dataset, I want to be a reference
1
#1 opened about 3 years ago
by
joushe