Junwon Hwang
nuxlear
AI & ML interests
LLM / Optimization
Recent Activity
new activity
about 9 hours ago
LGAI-EXAONE/K-EXAONE-236B-A23B:llama.cpp
upvoted
a
collection
2 days ago
K-EXAONE
liked
a model
2 days ago
LGAI-EXAONE/K-EXAONE-236B-A23B
Organizations
llama.cpp
1
#4 opened about 9 hours ago
by
jacek2024
Why does the EXAONE-4.0 chat_template strip <think> with [:9] instead of [:7]?
1
#13 opened about 1 month ago
by
kihunKim
question regarding the reasoning feature.
1
#12 opened 2 months ago
by
wowohuhud
Ollama Upload Plan
3
#9 opened 5 months ago
by
Timmothy
AWQ or GPTQ quantization?
2
#8 opened 5 months ago
by
lesj0610
update -ngl arg to count the output layer
1
#6 opened 6 months ago
by
owao
대체 뭘 만든건가요..
6
#2 opened 6 months ago
by
luckycontrol
Not loading the gguf
3
#2 opened 6 months ago
by
Trilogix1
CRASHING in kobold cpp for gguf file
1
#4 opened 6 months ago
by
VivekLeon
VLLM
1
#1 opened 6 months ago
by
chriswritescode
Not supported Jinja template in Exaone 4.0 llama.cpp fork
➕
2
7
#1 opened 6 months ago
by
InfernalDread
Fix jinja bugs，Reasoning mode is used by default
3
#2 opened 6 months ago
by
xldistance
Can't load model
👀
2
2
#1 opened 6 months ago
by
wonderfuldestruction
doesnt work (with anythingllm/ollama) #wontwork
2
#15 opened 8 months ago
by
jjwsl
transformers로 사용 안됨 / cannot try this model via transformers library
1
#6 opened 8 months ago
by
jjwsl
float32 please!!!!
1
#9 opened 10 months ago
by
ctranslate2-4you
Add links to paper and Github repository
👍
1
3
#3 opened 10 months ago
by
nielsr
Chat template difference with 32b
3
#2 opened 10 months ago
by
nbroad
Update configuration_exaone.py
1
#4 opened 10 months ago
by
sukrucildirr
How to properly run EXAONE-Deep-32B-AWQ with vLLM?
👍
1
2
#1 opened 10 months ago
by
hyunw55