Michael Shatskiy
YearZero
AI & ML interests
I'm interested in using LLM's for coding and logical reasoning.
Recent Activity
liked
a model
23 days ago
mradermacher/Wizard-Vicuna-13B-Uncensored-i1-GGUF
liked
a model
23 days ago
atultomar/vicuna-7b-v1.3-Q4_K_M-GGUF
new activity
about 1 month ago
bartowski/RekaAI_reka-flash-3-GGUF:Prompt template
Organizations
None yet
YearZero's activity
Prompt template
14
#1 opened about 1 month ago
by
YearZero
My brother in christ
#1 opened about 2 months ago
by
YearZero
Well this is a blast from the past!
3
#1 opened 4 months ago
by
YearZero
You think you could re-quant with the regex fix?
4
#3 opened 11 months ago
by
YearZero
🚩 Report: Ethical issue(s)
1
#2 opened about 1 year ago
by
YearZero
prompt template?
1
#4 opened about 1 year ago
by
YearZero
Prompt template?
2
#3 opened over 1 year ago
by
YearZero
failed to load the model
16
#1 opened over 1 year ago
by
rinoa
This model uses <0x0A> instead of a carriage return
8
#1 opened over 1 year ago
by
YearZero
Error during converting to gguf
3
#3 opened over 1 year ago
by
apepkuss79
Do we know if this is a base model or instruction tuned?
8
#1 opened over 1 year ago
by
YearZero
Q4_0 works great in Koboldcpp, Q4_K_M gives absolute gibberish.
3
#3 opened over 1 year ago
by
YearZero
BOS token as 1 seriously hurts these GGUF Yi models
11
#1 opened over 1 year ago
by
KerfuffleV2

Confirm prompt template
2
#1 opened almost 2 years ago
by
YearZero
Any chance for q8_0?
6
#1 opened almost 2 years ago
by
YearZero
Any chance for q8_0?
6
#1 opened almost 2 years ago
by
YearZero
Any chance for q8_0?
6
#1 opened almost 2 years ago
by
YearZero