Ben
usrlocalben
AI & ML interests
None yet
Organizations
None yet
Why does the chat template include reasoning/thinking components?
👀 1
#45 opened 2 months ago
by
usrlocalben
Kimi K2.5 using ktkernel + sglang, 16 TPS, but no starting <think> tag.
➕ 1
5
#28 opened 4 months ago
by
gyularabai
What is the H in HQ4_K?
2
#2 opened 9 months ago
by
usrlocalben
What's new in 3.0 vs 2.0?
2
#1 opened 9 months ago
by
usrlocalben
What actually is the EOS token for this model?
4
#31 opened 10 months ago
by
jukofyork
Thanks for the mainline llama.cpp PR effort!
❤️🔥 2
21
#1 opened 11 months ago
by
ubergarm
Any plans to release an updated version based on DeepSeek-V3-0526 + R1, or how to create the merge myself?
14
#4 opened about 1 year ago
by
Lissanro
Are there any changes in method vs. your v3-0324 quant?
3
#1 opened about 1 year ago
by
usrlocalben
Are there any changes in method vs. your v3-0324 quant?
3
#1 opened about 1 year ago
by
usrlocalben