Clayton Donley
CED6688
AI & ML interests
None yet
Organizations
None yet
This instruct model responds like a Thinking model - prompt template includes <think> as well
4
#1 opened 5 months ago
by
CED6688
MTP Accepted throughput always at 0.00 tokens/s
4
#5 opened 6 months ago
by
bpozdena
There's a HUGE drop in popular knowledge from v2 to v2.5.
๐ ๐ 14
29
#1 opened over 1 year ago
by
phil111
Nerfed with people
2
#17 opened over 1 year ago
by
spawn99
Can it be run on a 3090 with 24gb VRAM?
2
#18 opened over 1 year ago
by
mnemic
ImportError: cannot import name 'Qwen2VLForConditionalGeneration' from 'transformers'
8
#5 opened over 1 year ago
by
ananda296ai
LoRA Finetuning Tool for Qwen2-VL-7B in Web UI (DPO updated)
๐ 4
12
#2 opened over 1 year ago
by
hiyouga