DC
Downtown-Case
AI & ML interests
None yet
Recent Activity
new activity
9 days ago
Qwen/Qwen3-32B:Potential issue with large context sizes - can someone confirm?
liked
a model
15 days ago
lucyknada/maldv_QwentileLambda2.5-32B-Instruct-exl3-5bpw
new activity
17 days ago
ArtusDev/TheDrummer_Valkyrie-49B-v1_EXL3_3.0bpw_H6:HB is set to 8, not 6.
Organizations
None yet
Downtown-Case's activity
Potential issue with large context sizes - can someone confirm?
15
#18 opened about 1 month ago
by
Thireus
HB is set to 8, not 6.
🤝
1
1
#1 opened 17 days ago
by
Downtown-Case
Brainstorming
🧠
5
5
#6 opened about 1 month ago
by
Downtown-Case
Context size? YaRN still supported?
2
#3 opened about 1 month ago
by
Thireus
Base Model?
➕
😔
8
11
#3 opened about 1 month ago
by
Downtown-Case
Base Model?
8
#2 opened about 1 month ago
by
Downtown-Case
Is this a QAT model?
2
#2 opened about 1 month ago
by
Downtown-Case
Context Length?
1
#1 opened about 1 month ago
by
Downtown-Case
<think> token
1
#2 opened about 1 month ago
by
Downtown-Case
QAT version?
1
#1 opened about 1 month ago
by
Downtown-Case
Details?
#1 opened about 2 months ago
by
Downtown-Case
Script used?
3
#1 opened 2 months ago
by
Downtown-Case
Thanks.
👍
2
5
#1 opened 4 months ago
by
dinerburger

Are any of these the QAT releases of Gemma 3
6
#15 opened 3 months ago
by
Downtown-Case
good
👍
1
18
#1 opened 9 months ago
by
McUH
This looks great
6
#1 opened 7 months ago
by
DazzlingXeno
Is this trained off the base or instruct model?
2
#1 opened 8 months ago
by
Downtown-Case
Clarifications on how to use YaRN
5
#5 opened 8 months ago
by
Downtown-Case
128K usage?
2
#1 opened 9 months ago
by
Downtown-Case