Ljubomir Josifovski
ljupco
AI & ML interests
Now - ML/AI, agents, forecasting, science & engineering. Previous - systematic trading, research & development. Previous^2 - speech recognition in noise, speech synthesis, machine learning.
Recent Activity
liked a model about 3 hours ago
mindlab-research/Macaron-V1-Venti upvoted a paper about 5 hours ago
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget liked a model about 8 hours ago
Trilogix1/Hugston-Macaron-V1-TallOrganizations
None yet
Ling-3.0-flash?
➕ 1
#9 opened 4 days ago
by ljupco
Runs on M2 Max too
#1 opened 2 months ago
by ljupco
thank you! - running on llama.cpp on M2 Max now :-)
❤️🤗 2
1
#8 opened 3 months ago
by ljupco
good fit for M2 Max 96gb - it's 104B-A7B4
👍 1
#1 opened 3 months ago
by ljupco
GGUF quants and llama.cpp inference?
#7 opened 5 months ago
by ljupco
mlx-lm not ready
👍 5
12
#1 opened 11 months ago
by 
Weiguo
🚀 Best Practices for Evaluating the Qwen3-Next Model
🚀👍 7
1
#8 opened 11 months ago
by 
Yunxz
How does this compare to other "1M context"-s UloRL and Unsloth?
#5 opened 12 months ago
by ljupco
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma3n'
2
#3 opened about 1 year ago
by ljupco
provide int4 version pls
👀➕ 2
4
#2 opened about 1 year ago
by 
Josh1026
Is there any documentation about the sampling parameters maybe?
1
#1 opened about 1 year ago
by ljupco
Please share feedback here!
34
#6 opened about 1 year ago
by 
shimmyshimmer
Please share feedback here!
34
#6 opened about 1 year ago
by shimmyshimmer
Please share feedback here!
34
#6 opened about 1 year ago
by shimmyshimmer