Aoum
ai2p
AI & ML interests
None yet
Organizations
None yet
ai2p's activity
Why does it insert so many unsolicited http-links?
1
#9 opened over 1 year ago
by
ai2p
Is the q4 version in ggml format?
1
#4 opened over 1 year ago
by
ai2p
Есть ли в планах сконвертировать в ggml 4q формат для запуска на CPU?
2
#1 opened over 1 year ago
by
ai2p
Как запустить в llama.cpp на CPU?
#1 opened over 1 year ago
by
ai2p
Есть ли в планах сконвертировать в ggml 4q формат?
1
#2 opened over 1 year ago
by
ai2p
Will it be converted to ggml q4?
5
#1 opened over 1 year ago
by
ai2p
Any plan to create a 13b unfiltered model?
1
#7 opened over 1 year ago
by
ai2p
Did anyone managed to convert it to ggml 4bit for llama.cpp?
1
#6 opened over 1 year ago
by
wojhoiw
Is there a model based on this dataset yet?
78
#1 opened over 1 year ago
by
spanielrassler
Will it be possible to run this on PC with 8 GeForce RTX 3060 with 8 Gb VRAM each?
2
#11 opened over 1 year ago
by
ai2p
ggml conversion error
6
#1 opened over 1 year ago
by
Reggie
What is the source, not anon8231489123_vicuna-13b-GPTQ-4bit-128g?
1
#4 opened over 1 year ago
by
ai2p
Where did you get model weights from
3
#2 opened over 1 year ago
by
tarunchand
Outstanding Model
4
#3 opened over 1 year ago
by
Phew
Missing 3rd shard of the dataset?
1
#1 opened over 1 year ago
by
Eterna2