Mr. Finger
Apel-sin
AI & ML interests
I do optimized EXL2 quants for 48GB VRAM setups.
Recent Activity
liked
a model
about 16 hours ago
NousResearch/DeepHermes-3-Mistral-24B-Preview
updated
a model
9 days ago
Apel-sin/saiga_yandexgpt_8b-exl2
published
a model
9 days ago
Apel-sin/saiga_yandexgpt_8b-exl2
Organizations
None yet
Apel-sin's activity
Методология дообучения
#2 opened 11 days ago
by
Apel-sin

openai compatible API server
#7 opened 12 days ago
by
Apel-sin

не распознаются первые слова
1
#6 opened 16 days ago
by
Begemot-nn
finetuned model exists?
1
#1 opened about 1 month ago
by
dfsafdsf
This model is heavily censored. Can this finetuning be done ontop of an abliterated model?
3
#3 opened 5 months ago
by
Phr00t
Exllamav2 quant needed
3
#1 opened 3 months ago
by
zypcastles
Could you please create an EXL2 version?
#1 opened 5 months ago
by
Apel-sin

New data to train
1
#1 opened 5 months ago
by
Apel-sin

Can u make an exl2 version?
#1 opened 6 months ago
by
Apel-sin

Great model!
2
#4 opened 6 months ago
by
simplycorbett
Thanx for model
#8 opened 7 months ago
by
Apel-sin

My alternative quantizations.
3
#3 opened 8 months ago
by
ZeroWw
Can u make measurement.json for exl2 quantization?
#1 opened 8 months ago
by
Apel-sin

4.25bpw version
4
#1 opened 9 months ago
by
Apel-sin

You're the best!
#1 opened 9 months ago
by
Apel-sin

Smaug-Llama-3-70B-Instruct-32K
#3 opened 9 months ago
by
Apel-sin

Smaug-Llama-3-70B-Instruct-32K
#1 opened 9 months ago
by
Apel-sin

dolphin-2.9.2-codestral-22B
9
#2 opened 9 months ago
by
Apel-sin

exl quants please
2
#3 opened 10 months ago
by
rjmehta