Sevenof9
kalle07
AI & ML interests
Scientist, Teacher, Ai in Vision and LLM
Recent Activity
new activity 1 day ago
kai-os/Carnice-9b:comparison new activity 1 day ago
McGill-NLP/A3-Qwen3.5-2B:nice work liked a model 1 day ago
McGill-NLP/A3-Qwen3.5-2BOrganizations
comparison
#2 opened 1 day ago
by
kalle07
interessting but comparison
1
#1 opened 1 day ago
by
kalle07
lm-studio 0.4.11 with CUDA 12 llama.cpp (Windows) v2.13.0 dont run
1
#1 opened 1 day ago
by
kalle07
differ from other ???
#1 opened 1 day ago
by
kalle07
[Agent Evaluation] Testing CoPaw-Flash-9B as a local coding agent
5
#1 opened 17 days ago
by
FutureMa
How is the model supposed to be deployed with vLLM?
7
#1 opened 8 months ago
by
diuibyang
model quality
#1 opened 7 days ago
by
kalle07
This is just Qwen3-Embedding-8B
1
#1 opened about 1 month ago
by
darrowoflykos
seems a minmal trained model based on BGE-m3
#1 opened 15 days ago
by
kalle07
Lora support for this model
4
#1 opened about 2 months ago
by
merryman0080
not comparable 25steps vs 4steps
10
#2 opened 22 days ago
by
kalle07
base vs distill
#1 opened 22 days ago
by
kalle07
key argument for llama.cpp DIFFER
#24 opened 26 days ago
by
kalle07
oldhag88/qwen3.5-9b-nsfw-captioning-v3
1
#2066 opened 29 days ago
by
kalle07
never ending description
1
#1 opened 29 days ago
by
kalle07
oldhag88/qwen3.5-9b-nsfw-captioning-v2
1
#2053 opened about 1 month ago
by
kalle07
differences between quants
4
#1 opened about 1 month ago
by
kalle07